Need help with pr12?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

taeoh-kim
135 Stars 26 Forks 10 Commits 0 Opened issues

Description

Youtube Deep Learning Presentation

Services available

!
?

Need anything else?

Contributors list

PR12 Deep Learning Paper Presentation List and Summary

A Documentation of PR12 Deep Learning Paper Presentation Group on YouTube from Tensorflow-Korea Community

페이스북 Tensorflow-Korea PR12 유튜브 딥러닝 논문읽기 모임 논문 List-Up 및 요약 페이지입니다

수정 및 업데이트 요청: 김태오 (Taeoh Kim), [email protected]

Last Updated: 2019/11/23

Table of Contents

Papers by Topic

Up to PR-200

| Title | PR-001-to-100 | PR-101-to-200 | |:--------------------------------|:------------------------------------|:------------------------------------| | Network | | | | CNN | 002 011 020 028 034 083 | 123 155 163 169 170 177 | | RNN | 003 014 058 068 | | | Neural Networks | 043 | 138 174| | Network Compression | 009 026 033 044 054 072 078 | 105 108 111 120 144 156 180 183 184 187 193 194 197 200 | | Hardware | 085 | 111 | | Visualization | 047 053 | | | Memory Networks | 006 036 | | | Capsule Networks | 056 | | | Generative Models | | | | Generative Models | 001 010 022 024 040 048 051 087 088 | 101 116 125 136 137 142 144 174 192 | | GANs | 001 022 030 048 051 065 073 077 079 087 | 102 104 109 114 115 122 125 131 136 142 152 154 165 168 192 | | VAEs | 010 | 101 164 173 | | Autoregressive Models | 024 040 068 | | | Normalizing Flow Models | | 116 | | Computer Vision | | | | Classification | 020 021 026 028 034 044 054 083 090 | 108 119 120 123 156 163 169 170 171 183 196 198 | | Detection | 002 012 016 023 025 033 044 054 057 084 | 108 110 132 146 157 158 166 172 185 196 198 199 | | Segmentation | 008 045 057 100 | 123 126 141 159 200 | | Human/Body/Face | 014 | 102 126 127 135 165 171 185 | | 3D Single-View | 098 | | | 3D Multi-View | | 135 | | OCR | | 158 | | Image Restoration | 004 030 | 107 113 149 151 177 | | Video/Motion | 014 | 102 104 114 139 192 198 200 | | Style Transfer | 007 | 122 131 149 186 | | Image Translation | 065 073 | 102 104 114 152 154 165 168 179 | | Relational Reasoning | 018 095 | | | NLP/Text/Knowledge | | | | Representation | 027 049 076 099 | 121 145 161 175 | | Machine Translation | 003 055 | | | Question Answering | 037 | | | Text Classification | 015 037 | | | Text Generation | 077 | | | Text Style-Transfer | 059 | | | Knowledge Tracing | 046 | | | Audio/Speech | | | | Audio/Speech Enhancement | 067 | | | Audio/Speech Generation | 040 079 | | | Audio/Speech Style-Transfer | 091 | 128 | | Audio/Speech Separation | 082 | | | Multimodal | | | | Multimodal | 025 | 147 179 | | Vision and Language/Text | 032 041 074 082 | 147 179 | | CNN-RNN | 050 | | | Text-to-Speech | 074 | 179 | | Reinforcement Learning | | | | Reinforcement Learning | 005 017 019 029 052 077 081 093 100 | 130 143 | | Machine Learning | | | | Transfer Learning | 009 026 078 096 | 160 181 | | Domain Adaptation | 013 | 159 | | Optimization | 031 042 066 071 075 086 | 134 | | Attention | 011 049 055 083 | 161 163 179 196 | | Explainable AI | 035 047 053 089 | 106 140 167 181 | | Few/One/Zero Shot | 036 | 165 168 | | Bayesian/Uncertainty | 039 080 088 | | | Latent Space Models | 088 | | | Graph | 026 | 160 178 | | Dimension Reduction | | 112 124 | | Data Visualization | | 103 | | Weakly-supervised Learning | 047 053 | | | Semi-supervised Learning | | 178 189 195 | | Self-supervised Learning | 090 | 124 136 162 | | Anomaly Detection | | 115 148 190 | | Disentangled Representation | 010 022 | 101 137 164 | | Generalization | 061 062 066 075 | 140 150 176 181 182 189 190 195 | | Regularization | 061 | 182 | | Active Learning | | 119 | | Metric/Similarity Learning | | 127 139 147 151 171 | | Imitation Learning | | 130 | | Continual Learning | | 188 | | Normalization | 021 | 134 186 | | Distributed Training | 092 | 129 133 | | Counterfactual Inference | 097 | | | ML Fairness | | 191 | | AutoML | | | | Neural Architecture Search | 017 063 069 | 105 141 155 166 169 183 187 194 | | Hyperparameter Optimization | 080 | | | Meta-Learning | 031 094 | 153 188 | | Applications | | | | Medical | 008 | 159 173 177 | | Recommender System | 060 064 | | | Adversarial Attack | 038 | 117 118 | | Cloud | 070 | | | Data Acquisition/Annotation | | 157 |

Presenter

Paper Statistics

by Main Subject

| Title | PR-001-to-050 | PR-051-to-100 | PR-101-to-150 | PR-151-to-200 | |:------------------------|:--------------|:--------------|:--------------|:--------------| | Computer Vision | 29 | 13 | 26 | 31 | | Machine Learning | 21 | 20 | 20 | 20 | | NLP | 5 | 7 | 2 | 3 | | Reinforcement Learning | 3 | 3 | 2 | 0 | | Audio/Speech | 1 | 6 | 1 | 0 | | Text/Knowledge/Graph | 1 | 3 | 0 | 1 | | Hardware | 0 | 1 | 1 | 0 |

by Conferences/Journals

| Title | PR-001-to-050 | PR-051-to-100 | PR-101-to-150 | PR-151-to-200 | |:------------------------|:--------------|:--------------|:--------------|:--------------| | CVPR | 20 | 7 | 12 | 14 | | NeurIPS | 12 | 7 | 7 | 6 | | ICML | 6 | 9 | 4 | 7 | | ICLR | 9 | 12 | 7 | 5 | | ICCV | 1 | 3 | 1 | 5 | | ECCV | 0 | 0 | 7 | 2 | | EMNLP | 3 | 0 | 0 | 0 | | AAAI | 1 | 1 | 1 | 1 | | RecSys | 0 | 2 | 0 | 0 | | Interspeech | 0 | 2 | 0 | 0 | | ISCA | 0 | 1 | 1 | 0 | | SIGGRAPH | 0 | 1 | 0 | 0 | | ICASSP | 0 | 1 | 0 | 0 | | ECML-PKDD | 0 | 1 | 0 | 0 | | WACV | 0 | 0 | 1 | 0 | | ICCC | 0 | 0 | 1 | 0 | | IPMI | 0 | 0 | 1 | 0 | | BMVC | 0 | 0 | 0 | 2 | | ACL | 0 | 0 | 0 | 1 | | Arxiv/Blog/Tech Rpt. | 5 | 5 | 6 | 7 | | Journals | 3 | 1 | 3 | 4 |

by Published Year

| Title | PR-001-to-050 | PR-051-to-100 | PR-101-to-150 | PR-151-to-200 | |:------------------------|:--------------|:--------------|:--------------|:--------------| | 2019 | 0 | 2 | 11 | 25 | | 2018 | 0 | 18 | 23 | 15 | | 2017 | 23 | 20 | 8 | 9 | | 2016 | 14 | 7 | 5 | 3 | | 2015 | 14 | 2 | 1 | 1 | | 2014 | 7 | 2 | 0 | 0 | | 2013 | 1 | 0 | 0 | 0 | | ~2012 | 1 | 2 | 4 | 1 |

PR-001 ~ PR-050

PR-001: Generative Adversarial Nets

  • Paper, Video
  • Ian J. Goodfellow et al., NIPS 2014
  • Keywords: Generative Models, GANs
  • Presenter: Jaejun Yoo
  • [Top]

PR-002: Deformable Convolutional Networks

  • Paper, Video
  • Jifeng Dai et al., CVPR 2017
  • Keywords: CNN, Detection
  • Presenter: Terry TaeWoong Um
  • [Top]

PR-003: Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

  • Paper, Video
  • Kyunghyun Cho et al., EMNLP 2014
  • Keywords: NLP, RNN, Machine Translation
  • Presenter: Keunbong Kwak
  • [Top]

PR-004: Image Super-Resolution using Deep Convolutional Neural Networks

  • Paper, Video
  • Chao Dong et al., CVPR 2015
  • Keywords: Image Restoration
  • Presenter: Taegyun Jeon
  • [Top]

PR-005: Playing Atari with Deep Reinforcement Learning

  • Paper, Video
  • Volodymyr Mnih et al., NIPS 2013 Workshop
  • Keywords: Reinforcement Learning
  • Presenter: Sunghun Kim
  • [Top]

PR-006: Neural Turing Machines

  • Paper, Video
  • Alex Graves et al., Arxiv 2014
  • Keywords: Memory Networks
  • Presenter: Kiho Suh
  • [Top]

PR-007: Deep Photo Style Transfer

  • Paper, Video
  • Fujun Luan et al., CVPR 2017
  • Keywords: Style Transfer
  • Presenter: Seungil Kim
  • [Top]

PR-008: Reverse Classification Accuracy: Predicting Segmentation Performance in the Absence of Ground Truth

  • Paper, Video
  • Vanya V. Valindria et al., IEEE Transactions on Medical Imaging, 2017
  • Keywords: Medical, Segmentation
  • Presenter: Dongjun Jung
  • [Top]

PR-009: Distilling the Knowledge in a Neural Network

  • Paper, Video
  • Geoffrey Hinton et al., NIPS 2014 Workshop
  • Keywords: Network Compression, Transfer Learning
  • Presenter: Young Jae Choung
  • [Top]

PR-010: Auto-Encoding Variational Bayes

  • Paper, Video
  • Diederik P Kingma and Max Welling, ICLR 2014
  • Keywords: Generative Models, VAEs, Disentangled Representation
  • Presenter: Junbum Cha
  • [Top]

PR-011: Spatial Transformer Networks

  • Paper, Video
  • Max Jaderberg et al., NIPS 2015
  • Keywords: CNN, Attention
  • Presenter: Jiyang Kang
  • [Top]

PR-012: Faster R-CNN: Towards Real-time Object Detection with Region Proposal Networks

  • Paper, Video
  • Shaoqing Ren et al., NIPS 2015
  • Keywords: Detection
  • Presenter: Jinwon Lee
  • [Top]

PR-013: Domain Adversarial Training of Neural Network

  • Paper, Video
  • Yaroslav Ganin et al., JMLR 2016
  • Keywords: Domain Adaptation
  • Presenter: Jaejun Yoo
  • [Top]

PR-014: On Human Motion Prediction using RNNs

  • Paper, Video
  • Julieta Martinez et al., CVPR 2017
  • Keywords: RNN, Human/Body/Face, Video/Motion
  • Presenter: Terry TaeWoong Um
  • [Top]

PR-015: Convolutional Neural Networks for Sentence Classification

  • Paper, Video
  • Yoon Kim, EMNLP 2014
  • Keywords: NLP, Text Classification
  • Presenter: Keunbong Kwak
  • [Top]

PR-016: You Only Look Once: Unified, Real-time Object Detection

  • Paper, Video
  • Joseph Redmon et al., CVPR 2016
  • Keywords: Detection
  • Presenter: Taegyun Jeon
  • [Top]

PR-017: Neural Architecture Search with Reinforcement Learning

  • Paper, Video
  • Barret Zoph and Quoc V. Le, ICLR 2017
  • Keywords: Neural Architecture Search, Reinforcement Learning
  • Presenter: Kiho Suh
  • [Top]

PR-018: A Simple Neural Network Module for Relational Reasoning

  • Paper, Video
  • Adam Santoro et al., NIPS 2017
  • Keywords: Relational Reasoning
  • Presenter: Sunghun Kim
  • [Top]

PR-019: Continuous Control with Deep Reinforcement Learning

  • Paper, Video
  • Timothy P. Lillicrap et al., Arxiv 2015
  • Keywords: Reinforcement Learning
  • Presenter: Seungil Kim
  • [Top]

PR-020: Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

  • Paper, Video
  • Kaiming He et al., ICCV 2015
  • Keywords: CNN, Classification
  • Presenter: Jiyang Kang
  • [Top]

PR-021: Batch Normalization

  • Paper, Video
  • Sergey Loffe and Christian Szegedy, ICML 2015
  • Keywords: Classification, Normalization
  • Presenter: Young Jae Choung
  • [Top]

PR-022: InfoGAN

  • Paper, Video
  • Xi Chen at al., NIPS 2016
  • Keywords: Generative Models, GANs, Disentangled Representation
  • Presenter: Junbum Cha
  • [Top]

PR-023: YOLO9000: Better, Faster, Stronger

  • Paper, Video
  • Joseph Redmon and Ali Farhadi, CVPR 2017
  • Keywords: Detection
  • Presenter: Jinwon Lee
  • [Top]

PR-024: Pixel Recurrent Neural Network

  • Paper, Video
  • Aaron van den Oord et al., ICML 2016
  • Keywords: Generative Models, Autoregressive Models
  • Presenter: Jaejun Yoo
  • [Top]

PR-025: Learning with Side Information through Modality Hallucination

  • Paper, Video
  • Judy Hoffman et al., CVPR 2016
  • Keywords: Multimodal, Detection
  • Presenter: Terry TaeWoong Um
  • [Top]

PR-026: Notes for CVPR 2017 (3 Papers)

  • Paper1, Paper2, Paper3, Video
  • Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuning by Weifeng Ge and Yizhou Yu
  • The More You Know: Using Knowledge Graphs for Image Classification by Kenneth Marino et al.
  • On Compressing Deep Models by Low Rank and Sparse Decomposition by Xiyu Yu at al.
  • Keywords: Transfer Learning, Graph Networks, Classification, Network Compression
  • Presenter: Taegyun Jeon
  • [Top]

PR-027: GloVe: Global Vectors for Word Representation

  • Paper, Video
  • Jeffrey Pennington et al., EMNLP 2014
  • Keywords: NLP, Representation
  • Presenter: Keunbong Kwak
  • [Top]

PR-028: Densely Connected Convolutional Networks

  • Paper, Video
  • Gao Huang et al., CVPR 2017
  • Keywords: CNN, Classification
  • Presenter: Sunghun Kim
  • [Top]

PR-029: Apprenticeship Learning via Inverse Reinforcement Learning

  • Paper, Video
  • Pieter Abbeel and Andrew Y. Ng, ICML 2004
  • Keywords: Reinforcement Learning
  • Presenter: Kiho Suh
  • [Top]

PR-030: Photo-Realistic Single Image Super Resolution Using a Generative Adversarial Networks

  • Paper, Video
  • Christian Ledig et al., CVPR 2017
  • Keywords: GANs, Image Restoration
  • Presenter: Seungil Kim
  • [Top]

PR-031: Learning to Learn by Gradient Descent by Gradient Descent

  • Paper, Video
  • Marcin Andrychowicz et al., NIPS 2016
  • Keywords: Meta-Learning, Optimization
  • Presenter: Junbum Cha
  • [Top]

PR-032: Deep Visual-Semantic Alignments for Generating Image Descriptions

  • Paper, Video
  • Andrej Karpathy and Li Fei Fei, CVPR 2015
  • Keywords: Vision and Language/Text
  • Presenter: Jiyang Kang
  • [Top]

PR-033: PVANet: Lightweight Deep Neural Networks for Real-time Object Detection

  • Paper, Video
  • Sanghoon Hong et al., NIPS 2016 Workshop
  • Keywords: Detection, Network Compression
  • Presenter: Jinwon Lee
  • [Top]

PR-034: Inception and Xception (4 Papers)

  • Paper1, Paper2, Paper3, Paper4, Video
  • Going Deeper with Convolutions by Christian Szegedy at al. CVPR 2015
  • Rethinking the Inception Architecture for Computer Vision by Christian Szegedy at al. CVPR 2016
  • Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning by Christian Szegedy at al. AAAI 2017
  • Xception: Deep Learning with Depthwise Separable Convolutions by Francois Chollet, CVPR 2017
  • Keywords: CNN, Classification
  • Presenter: Jaejun Yoo
  • [Top]

PR-035: Understanding Black-box Predictions via Influence Functions

  • Paper, Video
  • Pang Wei Koh and Percy Liang, ICML 2017
  • Keywords: Explainable AI
  • Presenter: Terry TaeWoong Um
  • [Top]

PR-036: Learning to Remember Rate Events

  • Paper, Video
  • Lukasz Kaiser et al., ICLR 2017
  • Keywords: Few Shot Learning, Memory Networks
  • Presenter: Taegyun Jeon
  • [Top]

PR-037: Ask Me Anything: Dynamic Memory Networks for Natural Language Processing

  • Paper, Video
  • Ankit Kumar et al., ICML 2016
  • Keywords: NLP, Question Answering, Text Classification
  • Presenter: Keunbong Kwak
  • [Top]

PR-038: Explaining and Harnessing Adversarial Examples (2 Papers)

  • Paper1, Paper2, Video
  • Ian J. Goodfellow et al., ICLR 2015
  • Adversarial Attacks on Neural Network Policies by Sandy Huang et al., ICLR 2017 Workshop
  • Keywords: Adversarial Attack
  • Presenter: Kiho Suh
  • [Top]

PR-039: Dropout as a Bayesian Approximation

  • Paper, Video
  • Yarin Gal and Zoubin Ghahramani, ICML 2016
  • Keywords: Bayesian ML
  • Presenter: Junbum Cha
  • [Top]

PR-040: WaveNet: A Generative Model for Raw Audio

  • Paper, Video
  • Aaron van den Oord et al., Arxiv 2016
  • Keywords: Generative Models, Autoregressive Models, Audio/Speech Generation
  • Presenter: Seungil Kim
  • [Top]

PR-041: Show and Tell: A Neural Image Caption Generator

  • Paper, Video
  • Oriol Vinyals et al., CVPR 2015
  • Keywords: Vision and Language/Text
  • Presenter: Jiyang Kang
  • [Top]

PR-042: Adam: A Method for Stochastic Optimization

  • Paper, Video
  • Diederik P. Kingma and Jimmy Ba, ICLR 2015
  • Keywords: Optimization
  • Presenter: Ji-Hoon Kim
  • [Top]

PR-043: HyperNetworks

  • Paper, Video
  • David Ha et al., ICLR 2017
  • Keywords: Neural Networks
  • Presenter: Taesu Kim
  • [Top]

PR-044: MobileNet

  • Paper, Video
  • Andrew G. Howard et al., Arxiv 2017
  • Keywords: Network Compression, Classification, Detection
  • Presenter: Jinwon Lee
  • [Top]

PR-045: DeepLab: Semantic Image Segmentation (5 Papers)

  • Paper1, Paper2, Paper3, Paper4, Paper5, Video
  • Liang-Chieh Chen at al., ICLR 2015 and TPAMI 2016
  • Fully Convolutional Network for Semantic Segmentation by Jonathan Long et al., CVPR 2015
  • Multi Scale Context Aggregation by Dilated Convolution by Fisher Yu and Vladlen Koltun, ICLR 2016
  • PSPNet: Pyramid Scene Parsing Network by Hengshuang Zhao et al., CVPR 2017
  • Rethinking Atrous Convolution for Semantic Image Segmentation by Liang-Chieh Chen et al., Arxiv 2017
  • Keywords: Segmentation
  • Presenter: Taeoh Kim
  • [Top]

PR-046: Deep Knowledge Tracing

  • Paper, Video
  • Chris Piech at al., NIPS 2015
  • Keywords: Text/Knowledge
  • Presenter: Byung-Hak Kim
  • [Top]

PR-047: Learning Deep Features for Discriminative Localization

  • Paper, Video
  • Bolei Zhou et al., CVPR 2016
  • Keywords: Explainable AI, Visualization, Weakly-Supervised Learning
  • Presenter: KwangHee Lee
  • [Top]

PR-048: Towards Principled Methods for Training Generative Adversarial Networks

  • Paper, Video
  • Martin Arjovsky and Leon Bottou, ICLR 2017
  • Keywords: Generative Models, GANs
  • Presenter: Ji-Hoon Kim
  • [Top]

PR-049: Attention is All You Need

  • Paper, Video
  • Ashish Vaswani et al., NIPS 2017
  • Keywords: NLP, Attention, Representation
  • Presenter: Kiho Suh
  • [Top]

PR-050: Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting

  • Paper, Video
  • Xingjian Shi et al., NIPS 2015
  • Keywords: CNN-RNN
  • Presenter: Taegyun Jeon
  • [Top]

PR-051 ~ PR-100

PR-051: Conditional Generative Adversarial Nets

  • Paper, Video
  • Mehdi Mirza and Simon Osindero, Arxiv 2014
  • Keywords: Generative Models, GANs
  • Presenter: Seungil Kim
  • [Top]

PR-052: Mastering the Game of Go without Human Knowledge

  • Paper, Video (Not Available)
  • David Silver et al., Nature 2017
  • Keywords: Reinforcement Learning
  • Presenter: Junbum Cha
  • [Top]

PR-053: Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization

  • Paper, Video
  • Ramprasaath R. Selvaraju et al., ICCV 2017
  • Keywords: Explainable AI, Visualization, Weakly-Supervised Learning
  • Presenter: Taesu Kim
  • [Top]

PR-054: ShuffleNet: An Extremely Efficient CNN for Mobile Devices

  • Paper, Video
  • Xiangyu Zhang et al., CVPR 2018
  • Keywords: Compression, Classification, Detection
  • Presenter: Jinwon Lee
  • [Top]

PR-055: Neural Machine Translation by Jointly Learning to Align and Translate

  • Paper, Video
  • Dzmitry Bahdanau et al., ICLR 2015
  • Keywords: NLP, Machine Translation, Attention
  • Presenter: Jiyang Kang
  • [Top]

PR-056: Capsule Network

  • Paper, Video
  • Dynamic Routing Between Capsules by Sara Sabour et al., NIPS 2017
  • Keywords: Capsule Network
  • Presenter: Jaejun Yoo
  • [Top]

PR-057: Mask R-CNN

  • Paper, Video
  • Kaiming He et al., ICCV 2017
  • Keywords: Detection, Segmentation
  • Presenter: Taeoh Kim
  • [Top]

PR-058: The Consciousness Prior

  • Paper, Video
  • Yoshua Bengio, Arxiv 2017
  • Keywords: RNN, NLP
  • Presenter: Byung-Hak Kim
  • [Top]

PR-059: Style Transfer from Non-Parallel Text by Cross-Alignment

  • Paper, Video
  • Tianxiao Shen et al., NIPS 2017
  • Keywords: NLP, Text Style Transfer
  • Presenter: Kiho Suh
  • [Top]

PR-060: Deep Neural Networks for YouTube Recommendations

  • Paper, Video
  • Paul Covington et al., ACM Conference on Recommender Systems 2016
  • Keywords: Recommender System
  • Presenter: Keunbong Kwak
  • [Top]

PR-061: Understanding Deep Learning Requires Rethinking Generalization

  • Paper, Video
  • Chiyuan Zhang et al., ICLR 2017
  • Keywords: Generalization, Regularization
  • Presenter: Jaejun Yoo
  • [Top]

PR-062: Deep Learning: A Critical Appraisal

  • Paper, Video
  • Gary Marcus, Arxiv 2018
  • Keywords: Generalization
  • Presenter: Terry TaeWoong Um
  • [Top]

PR-063: Peephole: Predicting Network Performance Before Training

  • Paper, Video
  • Boyang Deng et al., Arxiv 2017
  • Keywords: NAS
  • Presenter: Taegyun Jeon
  • [Top]

PR-064: Wide & Deep Learning for Recommender Systems

  • Paper, Video
  • Heng-Tze Cheng et al., ACM Workshop on Deep Learning for Recommender Systems 2016
  • Keywords: Recommender System
  • Presenter: Keunbong Kwak
  • [Top]

PR-065: High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

  • Paper, Video
  • Ting-Chun Wang et al., CVPR 2018
  • Keywords: GANs, Image Translation
  • Presenter: KwangHee Lee
  • [Top]

PR-066: Don't Decay the Learning Rate, Increase the Batch Size

  • Paper, Video
  • Samuel L. Smith et al., ICLR 2018
  • Keywords: Optimization, Generalization
  • Presenter: Junbum Cha
  • [Top]

PR-067: Audio Super Resolution using Neural Nets

  • Paper, Video
  • Volodymyr Kuleshov et al., ICLR 2017 Workshop
  • Keywords: Audio/Speech, Speech Enhancement
  • Presenter: Seungil Kim
  • [Top]

PR-068: DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks

  • Paper, Video
  • David Salinas et al., ICML 2017
  • Keywords: RNN, Autoregressive Models
  • Presenter: Jiyang Kang
  • [Top]

PR-069: Efficient Neural Architecture Search via Parameter Sharing

  • Paper, Video
  • Hieu Pham et al., ICML 2018
  • Keywords: NAS
  • Presenter: Jinwon Lee
  • [Top]

PR-070: SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud

  • Paper, Video
  • Zahra Ghodsi et al., ICML 2018
  • Keywords: Cloud-based ML
  • Presenter: Taesu Kim
  • [Top]

PR-071: Categorical Reparameterization with Gumbel Softmax

  • Paper1, Paper2, Video
  • Eric Jang et al., NIPS 2016 Workshop
  • The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables by Chris J Maddison et al., ICLR 2017
  • Keywords: Optimization
  • Presenter: Jaejun Yoo
  • [Top]

PR-072: Deep Compression

  • Paper, Video
  • Song Han et al., ICLR 2016
  • Keywords: Network Compression
  • Presenter: Taeoh Kim
  • [Top]

PR-073: Generative Semantic Manipulation with Contrasting GAN

  • Paper, Video
  • Xiaodan Liang et al., NIPS 2017
  • Keywords: GANs, Image Translation
  • Presenter: KwangHee Lee
  • [Top]

PR-074: ObamaNet: Photo-Realistic Lip-Sync from Text

  • Paper, Video
  • Rithesh Kumar et al., NIPS 2017 Workshop
  • Keywords: Vision and Language/Text, Text-to-Speech
  • Presenter: Byung-Hak Kim
  • [Top]

PR-075: On Calibriation of Modern Neural Networks

  • Paper, Video
  • Chuan Guo et al., ICML 2017
  • Keywords: Generalization, Optimization
  • Presenter: Terry TaeWoong Um
  • [Top]

PR-076: Distributed Representations of Sentences and Documents

  • Paper, Video
  • Quoc V. Le and Tomas Mikolov, ICML 2014
  • Keywords: NLP, Representation
  • Presenter: Keunbong Kwak
  • [Top]

PR-077: SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient

  • Paper, Video
  • Lantao Yu et al., AAAI 2017
  • Keywords: NLP, GANs, Text Generation, Reinforcement Learning
  • Presenter: Kiho Suh
  • [Top]

PR-078: Net2Net: Accelerating Learning via Knowledge Transfer

  • Paper, Video
  • Tianqi Chen et al., ICLR 2016
  • Keywords: Network Compression, Transfer Learning
  • Presenter: Junbum Cha
  • [Top]

PR-079: Synthesizing Audio with Generative Adversarial Networks (Adversarial Audio Synthesis)

  • Paper, Video
  • Chris Donahue et al., ICLR 2019
  • Keywords: Audio/Speech, Audio/Speech Generation, GANs
  • Presenter: Seungil Kim
  • [Top]

PR-080: Practical Bayesian Optimization of Machine Learning Algorithms

  • Paper, Video
  • Jasper Snoek et al., NIPS 2012
  • Keywords: Hyperparameter Optimization, Bayesian ML
  • Presenter: Seungil Kim
  • [Top]

PR-081: Machine Theory of Mind

  • Paper, Video (Not Available)
  • Neil C. Rabinowitz et al., ICML 2018
  • Keywords: Reinforcement Learning
  • Presenter: Ji-Hoon Kim
  • [Top]

PR-082: Introduction to Speech Separation

  • Paper1, Paper2, Video
  • Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation by Ariel Ephrat et al., SIGGRAPH 2018
  • The Conversation: Deep Audio-Visual Speech Enhancement by Triantafyllos Afouras et al., Interspeech 2018
  • Keywords: Audio/Speech, Speech Separation, Vision and Language/Text
  • Presenter: Taesu Kim
  • [Top]

PR-083: Non-Local Neural Networks

  • Paper, Video
  • Xiaolong Wang et al., CVPR 2018
  • Keywords: CNN, Attention, Classification
  • Presenter: Taeoh Kim
  • [Top]

PR-084: MegDet: A Large Mini-Batch Object Detector

  • Paper, Video
  • Chao Peng et al., CVPR 2018
  • Keywords: Detection
  • Presenter: Taegyun Jeon
  • [Top]

PR-085: In-Datacenter Performance Analysis of a Tensor Processing Unit

  • Paper, Video
  • Norman P. Jouppi et al., ISCA 2017
  • Keywords: Hardware
  • Presenter: Jinwon Lee
  • [Top]

PR-086: Curriculum Learning

  • Paper, Video
  • Yoshua Bengio et al., ICML 2009
  • Keywords: Optimization
  • Presenter: Junbum Cha
  • [Top]

PR-087: Spectral Normalization for Generative Adversarial Networks

  • Paper, Video
  • Takeru Miyato et al., ICLR 2018
  • Keywords: Generative Models, GANs
  • Presenter: Jaejun Yoo
  • [Top]

PR-088: Deep Variational Bayes Filters

  • Paper, Video
  • Maximilian Karl et al., ICLR 2017
  • Keywords: Generative Models, Latent Space Models, Bayesian ML
  • Presenter: Terry TaeWoong Um
  • [Top]

PR-089: Beyond Word Importance: Contextual Decomposition to Extract Interactions

  • Paper, Video
  • W. James Murdoch et al., ICLR 2018
  • Keywords: NLP, Explainable AI
  • Presenter: Byung-Hak Kim
  • [Top]

PR-090: Representation Learning by Learning to Count

  • Paper, Video
  • Mehdi Noroozi et al., ICCV 2017
  • Keywords: Self-supervised Learning, Classification
  • Presenter: Kiho Suh
  • [Top]

PR-091: A Unversal Music Translation Network

  • Paper, Video
  • Noam Mor et al., ICLR 2019
  • Keywords: Audio/Speech, Audio Style Transfer
  • Presenter: Seungil Kim
  • [Top]

PR-092: Distributed Training of Neural Networks

  • Paper1, Paper2 Video
  • Scalable Distributed DNN Training Using Commodity GPU Cloud Computing by Nikko Strom, Interspeech 2015
  • Scalable Training of Deep Learning Machines by Incremental Block Training with Intra-block Parallel Optimization and Blockwise Model-Update Filtering by Kai Chen and Qiang Huo, ICASSP 2016
  • Keywords: Distibuted Training
  • Presenter: Jiyang Kang
  • [Top]

PR-093: Playing Hard Exploration Games by Watching YouTube

  • Paper, Video (Not Available)
  • Yusuf Aytar et al., NeurIPS (NIPS) 2018
  • Keywords: Reinforcement Learning
  • Presenter: Ji-Hoon Kim
  • [Top]

PR-094: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

  • Paper, Video
  • Chelsea Finn et al., ICML 2017
  • Keywords: Meta-Learning
  • Presenter: Taesu Kim
  • [Top]

PR-095: Modularity Matters: Learning Invariant Relational Reasoning Tasks

  • Paper, Video
  • Jason Jo et al., Arxiv 2018
  • Keywords: Relational Reasoning
  • Presenter: Jinwon Lee
  • [Top]

PR-096: Taskonomy: Disentangling Task Transfer Learning

  • Paper, Video
  • Amir Zamir et al., CVPR 2018
  • Keywords: Transfer Learning
  • Presenter: Taeoh Kim
  • [Top]

PR-097: Learning Representations for Counterfactual Inference

  • Paper, Video
  • Fredrik D. Johansson et al., ICML 2016
  • Keywords: Counterfactual Inference
  • Presenter: Byung-Hak Kim
  • [Top]

PR-098: MegaDepth: Leraning Single-View Depth Prediction from Internet Photos

  • Paper, Video
  • Zhengqi Li and Noah Snavely, CVPR 2018
  • Keywords: 3D Single-View
  • Presenter: KwangHee Lee
  • [Top]

PR-099: MRNet-Product2Vec: A Multi-Task Recurrent Neural Network for Product Embeddings

  • Paper, Video
  • Arijit Biswas et al., ECML-PKDD 2017
  • Keywords: NLP, Representation
  • Presenter: Keunbong Kwak
  • [Top]

PR-100: SeedNet: Automatic Seed Generation With Deep Reinforcement Learning for Robust Interactive Segmentation

  • Paper, Video
  • Gwangmo Song et al., CVPR 2018
  • Keywords: Segmentation, Reinforcement Learning
  • Presenter: KwangHee Lee
  • [Top]

PR-101 ~ PR-150

PR-101: Deep Feature Consistent Variational Autoencoder

  • Paper, Video
  • Xianxu Hou et al., WACV 2017
  • Keywords: Generative Models, VAEs, Disentangled Representation
  • Presenter: MinGuk Kang
  • [Top]

PR-102: Everybody Dance Now

  • Paper, Video
  • Caroline Chan et al., ICCV 2019
  • Keywords: GANs, Image Translation, Human/Body/Face, Video/Motion
  • Presenter: Byung-Hak Kim
  • [Top]

PR-103: Visualizing Data using t-SNE

  • Paper, Video
  • Laurens van der Maaten and Geoffrey Hinton, JMLR 2008
  • Keywords: Data Visualization
  • Presenter: Taeoh Kim
  • [Top]

PR-104: Video-to-Video Synthesis

  • Paper, Video
  • Ting-Chen Wang et al., NeurIPS (NIPS) 2018
  • Keywords: GANs, Image Translation, Video/Motion
  • Presenter: Taesu Kim
  • [Top]

PR-105: MNasNet: Platform-Aware Neural Architecture Search for Mobile

  • Paper, Video
  • Mingxing Tan et al., CVPR 2019
  • Keywords: NAS, Compression
  • Presenter: Taekmin Kim
  • [Top]

PR-106: Learning to Explain: An Information-Theoretic Perspective on Model Interpretation

  • Paper, Video
  • Jianbo Chen et al., ICML 2018
  • Keywords: Explainable AI
  • Presenter: Jinsung Yoon
  • [Top]

PR-107: Image Inpainting for Irregular Holes using Partial Convolutions

  • Paper, Video
  • Guilin Liu et al., ECCV 2018
  • Keywords: Image Restoration
  • Presenter: Jiwon Jung
  • [Top]

PR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks

  • Paper, Video
  • Mark Sandler et al., CVPR 2018
  • Keywords: Compression, Classification, Detection
  • Presenter: Jinwon Lee
  • [Top]

PR-109: Large Scale GAN Training for High Fidelity Naturel Image Synthesis

  • Paper, Video
  • Andrew Brock et al., ICLR 2019
  • Keywords: GANs
  • Presenter: Yeoung Seok Kim
  • [Top]

PR-110: SNIP: An Anaylsis of Scale Invariance in Object Detection

  • Paper, Video
  • Bharat Singh and Larry S. Davis et al., CVPR 2018
  • Keywords: Detection
  • Presenter: Jaewon Lee
  • [Top]

PR-111: EVA2: Exploiting Temporal Redundancy in Live Computer Vision

  • Paper, Video
  • Mark Buckler et al., ISCA 2018
  • Keywords: Compression, Hardware
  • Presenter: Soyeon Kim
  • [Top]

PR-112: Independent Component Analysis

  • Paper, Video
  • Aapo Hyvarinen, IEEE Transactions on Neural Networks 1999
  • Keywords: Dimension Reduction
  • Presenter: Jae Duk Seo
  • [Top]

PR-113: The Perception Distortion Tradeoff

  • Paper, Video
  • Yochai Blau and Tomer Michaeli, CVPR 2018
  • Keywords: Image Restoration
  • Presenter: Taeoh Kim
  • [Top]

PR-114: Recycle-GAN: Unsupervised Video Retargeting

  • Paper, Video
  • Aayush Bansal et al., ECCV 2018
  • Keywords: GANs, Image Translation, Video/Motion
  • Presenter: Byung-Hak Kim
  • [Top]

PR-115: Unsupervised Anomaly Detection with Generative Adversarial Networks

  • Paper, Video
  • Thomas Schlegl et al., IPMI 2017
  • Keywords: GANs, Anomaly Detection
  • Presenter: MinGuk Kang
  • [Top]

PR-116: Glow: Generative Flow with Invertable 1x1 Convolutions

  • Paper, Video
  • Diederik P. Kingma and Prafulla Dhariwal, NeurIPS (NIPS) 2018
  • Keywords: Generative Models, Normalizing Flow Models
  • Presenter: Taesu Kim
  • [Top]

PR-117: PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks

  • Paper, Video
  • Jan Svoboda et al., ICLR 2019
  • Keywords: Adversarial Attack
  • Presenter: Taekmin Kim
  • [Top]

PR-118: Black-box Attacks with Limited Queries and Information

  • Paper, Video
  • Andrew Ilyas et al., ICML 2018
  • Keywords: Adversarial Attack
  • Presenter: Jinsung Yoon
  • [Top]

PR-119: Active Learning for Convolutional Neural Networks: A Core-Set Approach

  • Paper, Video
  • Ozan Sener and Silvio Savarese, ICLR 2018
  • Keywords: Active Learning, Classification
  • Presenter: Jiwon Jung
  • [Top]

PR-120: ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

  • Paper, Video
  • Ningning Ma et al., ECCV 2018
  • Keywords: Compression, Classification
  • Presenter: Jinwon Lee
  • [Top]

PR-121: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

  • Paper, Video
  • Jacob Devlin et al., Arxiv 2018
  • Keywords: NLP, Representation
  • Presenter: Young Seok Kim
  • [Top]

PR-122: CAN: Creative Adversarial Networks, Generating Art by Learning About Style and Deviating from Style Norms

  • Paper, Video
  • Ahmed Elgammal et al., ICCC 2017
  • Keywords: GANs, Style Transfer
  • Presenter: Jaewon Lee
  • [Top]

PR-123: Partial Convolution based Padding

  • Paper, Video
  • Guilin Liu et al., Arxiv 2018
  • Keywords: CNN, Classification, Segmentation
  • Presenter: Soyeon Kim
  • [Top]

PR-124: Stacked Denoising Autoencoders

  • Paper, Video
  • Pascal Vincent et al., JMLR 2010
  • Keywords: Self-supervised Learning, Autoencoders
  • Presenter: Jae Duk Seo
  • [Top]

PR-125: Energy-based Generative Adversarial Networks

  • Paper, Video
  • Junbo Zhao et al., ICLR 2017
  • Keywords: Generative Models, GANs
  • Presenter: MinGuk Kang
  • [Top]

PR-126: DensePose: Dense Human Pose Estimation in the Wild

  • Paper, Video
  • Riza Alp Guler et al., CVPR 2018
  • Keywords: Segmentation, Pose
  • Presenter: Byung-Hak Kim
  • [Top]

PR-127: FaceNet

  • Paper, Video
  • Florian Schroff et al., CVPR 2015
  • Keywords: Human/Body/Face, Metric Learning
  • Presenter: Taeoh Kim
  • [Top]

PR-128: TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer

  • Paper, Video
  • Sicong Huang et al., ICLR 2019
  • Keywords: Audio/Speech, Audio/Speech Style-Transfer
  • Presenter: Taesu Kim
  • [Top]

PR-129: Horovod: Fast and Easy Distributed Deep Learning in TensorFlow

  • Paper, Video
  • Alexander Sergeev and Mike Del Balso, Arxiv 2018
  • Keywords: Distributed Training
  • Presenter: Taekmin Kim
  • [Top]

PR-130: Generative Adversarial Imitation Learning

  • Paper, Video
  • Jonathan Ho and Stefano Ermon, NIPS 2016
  • Keywords: Imitation Learning, Reinforcement Learning
  • Presenter: Jinsung Yoon
  • [Top]

PR-131: A Style-Based Generator Architecture for Generative Adversarial Networks

  • Paper, Video
  • Tero Karras et al, CVPR 2019
  • Keywords: GANs, Style-Transfer
  • Presenter: Jiwon Jung
  • [Top]

PR-132: SSD: Single Shot MultiBox Detector

  • Paper, Video
  • Wei Liu et al, ECCV 2016
  • Keywords: Detection
  • Presenter: Jinwon Lee
  • [Top]

PR-133: Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

  • Paper, Video
  • Priya Goyal et al, Arxiv 2017
  • Keywords: Distributed Training
  • Presenter: Young Seok Kim
  • [Top]

PR-134: How Does Batch Normalization Help Optimization?

  • Paper, Video
  • Shibani Santurkar et al, NeurIPS (NIPS) 2018
  • Keywords: Optimization, Normalization
  • Presenter: Jaewon Lee
  • [Top]

PR-135: Photo Wake-Up: 3D Character Animation from a Single Photo

  • Paper, Video
  • Chung-Yi Weng et al, CVPR 2019
  • Keywords: 3D Multi-View, Human/Body/Pose
  • Presenter: Soyeon Kim
  • [Top]

PR-136: Self-Supervised Generative Adversarial Networks

  • Paper, Video
  • Ting Chen et al, CVPR 2019
  • Keywords: Self-supervised Learning, Generative Models, GANs
  • Presenter: MinGuk Kang
  • [Top]

PR-137: MINE: Mutual Information Neural Estimation

  • Paper, Video (Not Available)
  • Mohamed Ishmael Belghazi et al, ICML 2018
  • Keywords: Generative Models, Disentangled Representation
  • Presenter: Jae Duk Seo
  • [Top]

PR-138: Mixture Density Networks

  • Paper, Video
  • Christopher M. Bishop, 1994
  • Keywords: Neural Networks
  • Presenter: Byung-Hak Kim
  • [Top]

PR-139: Fully Convolutional Siemese Networks for Object Tracking

  • Paper, Video
  • Luca Bertinetto et al., ECCV 2016
  • Keywords: Video/Motion, Metric Learning
  • Presenter: Taeoh Kim
  • [Top]

PR-140: Training Set Debugging using Trusted Items

  • Paper, Video
  • Xuezhou Zhang et al., AAAI 2018
  • Keywords: Explainable AI, Generalization
  • Presenter: Taesu Kim
  • [Top]

PR-141: Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

  • Paper, Video
  • Chenxi Liu et al., CVPR 2019
  • Keywords: NAS, Segmentation
  • Presenter: Taekmin Kim
  • [Top]

PR-142: Wasserstein GAN

  • Paper1, Paper2, Video
  • Martin Arjovsky et al., ICML 2017
  • Improved Training of Wasserstein GANs by Ishaan Gulrajani et al., NIPS 2017
  • Keywords: Generative Models, GANs
  • Presenter: Jinsung Yoon
  • [Top]

PR-143: Recurrent World Models Facilitate Policy Evolution

  • Paper, Video
  • David Ha and Jurgen Schmidhuber, NeurIPS (NIPS) 2018
  • Keywords: Reinforcement Learning
  • Presenter: Jiwon Jung
  • [Top]

PR-144: SqueezeNext: Hardware-Aware Neural Network Design

  • Paper1, Paper2, Video
  • SqueezeNext: Amir Gholami et al., CVPR 2018
  • SqueezeNet: Forrest N. Iandola et al., ICLR 2017
  • Keywords: Compression, Classification
  • Presenter: Jinwon Lee
  • [Top]

PR-145: Language Models are Unsupervised Multitask Learners (OpenAI GPT-2)

  • Paper, Video
  • Alec Radford et al., OpenAI Blog 2019
  • Keywords: NLP, Representation
  • Presenter: Young Seok Kim
  • [Top]

PR-146: CornerNet: Detecting Objects as Paired Keypoints

  • Paper, Video
  • Hei Law and Jia Deng, ECCV 2018
  • Keywords: Detection
  • Presenter: Jaewon Lee
  • [Top]

PR-147: Learning Deep Structure-Preserving Image-Text Embeddings

  • Paper, Video
  • Liwei Wang et al., CVPR 2016
  • Keywords: Metric Learning, Vision and Language/Text, Multimodal
  • Presenter: Soyeon Kim
  • [Top]

PR-148: Deep Anomaly Detection using Geometric Transformations

  • Paper, Video
  • Izhak Golan and Ran El-Yaniv, NeurIPS (NIPS) 2018
  • Keywords: Anomaly Detection
  • Presenter: MinGuk Kang
  • [Top]

PR-149: Perceptual Losses for Real-Time Style Transfer and Super-Resolution

  • Paper, Video
  • Justin Johnson et al., ECCV 2016
  • Keywords: Style-Transfer, Image Restoration
  • Presenter: Byung-Hak Kim
  • [Top]

PR-150: ImageNet-trained CNNs are Biased Towards Textures

  • Paper, Video
  • Robert Geirhos et al., ICLR 2019
  • Keywords: Generalization
  • Presenter: Taeoh Kim
  • [Top]

PR-151 ~ PR-200

PR-151: The Unreasonable Effectiveness of Deep Features as a Perceptual Metric

  • Paper, Video
  • Richard Zhang et al., CVPR 2018
  • Keywords: Metric Learning, Image Restoration
  • Presenter: Taesu Kim
  • [Top]

PR-152: StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation

  • Paper, Video
  • Yunjey Choi et al., CVPR 2018
  • Keywords: GANs, Image Translation
  • Presenter: Jinsung Yoon
  • [Top]

PR-153: SNAIL: A Simple Neural Attentive Meta-Learner

  • Paper, Video
  • Nikhil Mishra et al., ICLR 2018
  • Keywords: Meta-Learning
  • Presenter: Taekmin Kim
  • [Top]

PR-154: Semantic Image Synthesis with Spatially-Adaptive Normalization

  • Paper, Video
  • Taesung Park et al., CVPR 2019
  • Keywords: GANs, Image Translation
  • Presenter: Jiwon Jung
  • [Top]

PR-155: Exploring Randomly Wired Neural Networks for Image Recognition

  • Paper, Video
  • Saining Xie et al., ICCV 2019
  • Keywords: CNN, NAS
  • Presenter: Jinwon Lee
  • [Top]

PR-156: ChannelNets: Compact and Efficient CNN via Channel-Wise Convolutions

  • Paper, Video
  • Hongyang Gao et al., NeurIPS (NIPS) 2018
  • Keywords: Compression, Classification
  • Presenter: Young Seok Kim
  • [Top]

PR-157: Best of Both Worlds: Human-Machine Collaboration for Object Annotation

  • Paper, Video
  • Olga Russakovsky et al., CVPR 2015
  • Keywords: Detection, Data Annotation
  • Presenter: Jaewon Lee
  • [Top]

PR-158: FOTS: Fast Oriented Text Spotting with a Unified Network

  • Paper, Video
  • Xuebo Liu et al., CVPR 2018
  • Keywords: OCR, Detection
  • Presenter: Soyeon Kim
  • [Top]

PR-159: SIFA: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation

  • Paper, Video
  • Cheng Chen et al., AAAI 2019
  • Keywords: Domain Adaptation, Segmentation, Medical
  • Presenter: Sunghoon Joo
  • [Top]

PR-160: GLoMo: Unsupervised Learning of Transferable Relational Graph

  • Paper, Video
  • Zhilin Yang et al., NeurIPS (NIPS) 2018
  • Keywords: NLP, Transfer Learning, Graph
  • Presenter: Doyup Lee
  • [Top]

PR-161: Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

  • Paper, Video
  • Zihang Dai et al., ACL 2019
  • Keywords: NLP, Attention, Representation
  • Presenter: Sungnam Park
  • [Top]

PR-162: DeepPermNet: Visual Permutation Learning

  • Paper, Video
  • Rodrigo Santa Cruz et al., CVPR 2017
  • Keywords: Self-supervised Learning
  • Presenter: MinGuk Kang
  • [Top]

PR-163: CNN Attention Networks

  • Paper1, Paper2, Paper3, Paper4, Video
  • RAN (Residual Attention Network) by Fei Wang et al., CVPR 2017
  • BAM (Bottleneck Attention Module) by Jongchan Park et al., BMVC 2018
  • CBAM (Convolutional Block Attention Module) by Sanghyun Yoo et al., ECCV 2018
  • SE-Net (Squeeze and Excitation Networks) by Jie Hu., CVPR 2018
  • Keywords: CNN, Attention, Classification
  • Presenter: Taeoh Kim
  • [Top]

PR-164: InfoVAE: Balancing Learning and Inference in Variational Autoencoders

  • Paper, Video
  • Shengjia Zhao et al., Arxiv 2017
  • Keywords: VAEs, Disentangled Representation
  • Presenter: Byung-Hak Kim
  • [Top]

PR-165: Few-Shot Adversarial Learning of Realistic Neural Talking Head Models

  • Paper, Video
  • Egor Zakharov et al., Arxiv 2019
  • Keywords: Few-Shot Learning, GANs, Image Translation, Human/Body/Face
  • Presenter: Taesu Kim
  • [Top]

PR-166: NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

  • Paper, Video
  • Golnaz Ghiasi et al., CVPR 2019
  • Keywords: NAS, Detection
  • Presenter: Taekmin Kim
  • [Top]

PR-167: Interpretability Beyond Feature Attribution: Testing with Concept Activation Vector (TCAV)

  • Paper, Video
  • Been Kim et al., ICML 2018
  • Keywords: Explainable AI
  • Presenter: Jinsung Yoon
  • [Top]

PR-168: Few Shot Unsupervised Image to Image Translation

  • Paper, Video
  • Ming-Yu Liu et al., ICCV 2019
  • Keywords: Few-Shot Learning, GANs, Image Translation
  • Presenter: Jiwon Jung
  • [Top]

PR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

  • Paper, Video
  • Mingxing Tan et al., ICML 2019
  • Keywords: CNN, NAS, Classification
  • Presenter: Jinwon Lee
  • [Top]

PR-170: Deep Residual Learning for Image Recognition

  • Paper1, Paper2, Video
  • ResNet v1 by Kaiming He et al., CVPR 2016
  • ResNet v2 by Kaiming He et al., ECCV 2016
  • Keywords: CNN, Classification
  • Presenter: Yeong Seok Kim
  • [Top]

PR-171: Large-Margin Softmax Loss for Convolutional Neural Networks

  • Paper, Video
  • Weiyang Liu et al., ICML 2016
  • Keywords: Metric Learning, Classification, Human/Body/Face
  • Presenter: Jaewon Lee
  • [Top]

PR-172: Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression

  • Paper, Video
  • Hamid Rezatofighi et al., CVPR 2019
  • Keywords: Detection
  • Presenter: Soyeon Kim
  • [Top]

PR-173: Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules

  • Paper, Video
  • Rafael Gomez-Bombarelli et al., ACS Central Science 2018
  • Keywords: VAEs, Medical
  • Presenter: Sunghoon Joo
  • [Top]

PR-174: Restricted Boltzmann Machine for Deep Belief Nets

  • Paper, Video
  • Geoffrey E. Hinton et al., Neural Computation 2006
  • Keywords: Neural Network, Generative Models
  • Presenter: MinGuk Kang
  • [Top]

PR-175: XLNet: Generalized Autoregressive Pretraining for Language Understanding

  • Paper, Video
  • Zhilin Yang et al., Arxiv 2019
  • Keywords: NLP, Representation
  • Presenter: Sungnam Park
  • [Top]

PR-176: Combating Label Noise in Deep Learning Using Abstention

  • Paper, Video
  • Sunil Thulasidasan et al., ICML 2019
  • Keywords: Generalization
  • Presenter: Doyup Lee
  • [Top]

PR-177: Framing U-Net via Deep Convolutional Framelets

  • Paper1, Paper2, Video
  • Yoseob Han and Jong Chul Ye, IEEE Transactions on Medical Imaging, 2017
  • Jong Chul Ye et al., SIAM Journal on Imaging Sciences, 2017
  • Keywords: CNN, Image Restoration, Medical
  • Presenter: Byung-Hak Kim
  • [Top]

PR-178: Graph Convolutional Networks

  • Paper, Video
  • Thomas N. Kipf and MAx Welling, ICLR 2017
  • Keywords: Graph Networks, Semi-supervised Learning
  • Presenter: Taeoh Kim
  • [Top]

PR-179: M3D-GAN: Multi-Modal Multi-Domain Translation with Universal Attention

  • Paper, Video
  • Shuang Ma et al., ICLR 2017
  • Keywords: Multimodal, Attention, Image Translation, Text-to-Speech, Vision and Language/Text
  • Presenter: Taesu Kim
  • [Top]

PR-180: The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

  • Paper, Video
  • Jonathan Frankle and Michael Carbin, ICLR 2019
  • Keywords: Network Compression
  • Presenter: Taekmin Kim
  • [Top]

PR-181: Data Shapley: Equitable Valuation of Data for Machine Learning

  • Paper, Video
  • Amirata Ghorbani and James Zou, ICML 2019
  • Keywords: Explainable ML, Generalization, Transfer Learning
  • Presenter: Jinsung Yoon
  • [Top]

PR-182: Deep Learning Ensemble Methods

  • Video
  • Keywords: Generalization, Regularization
  • Presenter: Jiwon Jung
  • [Top]

PR-183: MixNet: Mixed Depthwise Convolutional Kernels

  • Paper, Video
  • Mingxing Tan and Quoc V. Le, BMVC 2019
  • Keywords: NAS, Compression, Classification, Detection
  • Presenter: Jinwon Lee
  • [Top]

PR-184: And the Bit Goes Down: Revisiting the Quantization of Neural Networks

  • Paper, Video
  • Pierre Stock et al., Arxiv 2019
  • Keywords: Compression
  • Presenter: Young Seok Kim
  • [Top]

PR-185: RetinaFace: Single-stage Dense Face Localisation in the Wild

  • Paper, Video
  • Jiankang Deng et al., Arxiv 2019
  • Keywords: Human/Body/Face, Detection
  • Presenter: Jaewon Lee
  • [Top]

PR-186: Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

  • Paper, Video
  • Xun Huang et al., ICCV 2017
  • Keywords: Style-Transfer, Normalization
  • Presenter: Soyeon Kim
  • [Top]

PR-187: MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks

  • Paper, Video
  • Ariel Gordon et al., CVPR 2018
  • Keywords: NAS, Compression
  • Presenter: Sunghoon Joo
  • [Top]

PR-188: Online Meta-Learning

  • Paper, Video
  • Chelsea Finn et al., ICML 2019
  • Keywords: Meta-Learning, Continual Learning
  • Presenter: Doyup Lee
  • [Top]

PR-189: Unsupervised Data Augmentation for Consistency Training

  • Paper, Video
  • Qizhe Xie et al., Arxiv 2019
  • Keywords: Semi-supervised Learning, Generalization
  • Presenter: Sungnam Park
  • [Top]

PR-190: A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks

  • Paper, Video
  • Dan Hendrycks and Kevin Gimpel, ICLR 2017
  • Keywords: Anomaly Detection, Generalization
  • Presenter: MinGuk Kang
  • [Top]

PR-191: Learning Adversarially Fair and Transferable Representations

  • Paper, Video
  • David Madras et al., ICML 2018
  • Keywords: ML Fairness
  • Presenter: Byung-Hak Kim
  • [Top]

PR-192: MoCoGAN: Decomposing Motion and Content for Video Generation

  • Paper, Video
  • Sergey Tulyakov et al., CVPR 2018
  • Keywords: Generative Models, GANs, Video/Motion
  • Presenter: Taeoh Kim
  • [Top]

PR-193: NISP: Pruning Networks using Neuron Importance Score Propagation

  • Paper, Video
  • Ruichi Yu et al., CVPR 2018
  • Keywords: Network Compression
  • Presenter: Taesu Kim
  • [Top]

PR-194: Once for All: Train One Network and Specialize it for Efficient Deployment

  • Paper, Video (Will be Uploaded)
  • Han Cai et al., Arxiv 2019
  • Keywords: Network Compression, NAS
  • Presenter: Taekmin Kim
  • [Top]

PR-195: MixMatch: A Holistic Approach to Semi-Supervised Learning

  • Paper, Video
  • David Berthelot et al., NeurIPS (NIPS) 2019
  • Keywords: Semi-supervised Learning, Generalization
  • Presenter: Jinsung Yoon
  • [Top]

PR-196: Stand-Alone Self-Attention in Vision Models

  • Paper, Video
  • Prajit Ramachandran et al., NeurIPS (NIPS) 2019
  • Keywords: Attention, Classification, Detection
  • Presenter: Jiwon Jung
  • [Top]

PR-197: One Ticket to Win Them All: Generalizing Lottery Ticket Initialization

  • Paper, Video
  • Ari S. Morcos et al., NeurIPS (NIPS) 2019
  • Keywords: Network Compression
  • Presenter: Jinwon Lee
  • [Top]

PR-198: TSM: Temporal Shift Module for Efficient Video Understanding

  • Paper, Video (Will be Uploaded)
  • Ji Lin et al., ICCV 2019
  • Keywords: Video Understanding, Classification, Detection
  • Presenter: Young Seok Kim
  • [Top]

PR-199: SNIPER : Efficient Multi-Scale Training

  • Paper, Video
  • Bharat Singh et al., NeurIPS (NIPS) 2018
  • Keywords: Detection
  • Presenter: Jaewon Lee
  • [Top]

PR-200: Online Model Distillation for Efficient Video Inference

  • Paper, Video
  • Ravi Teja Mullapudi et al., ICCV 2019
  • Keywords: Video/Motion, Compression, Segmentation
  • Presenter: Soyeon Kim
  • [Top]

PR-201 ~ PR-250

PR-201: Bag of Tricks for Image Classification with Convolutional Neural Networks

  • Paper, Video
  • Tong He et al., CVPR 2019
  • Keywords: Classification
  • Presenter: Jiyang Kang
  • [Top]

PR-202: Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts

  • Paper, Video
  • Jiaqi Ma et al., KDD 2018
  • Keywords: Recommender System
  • Presenter: Sungnam Park
  • [Top]

PR-203: Class-Balanced Loss Based on Effective Number of Samples

  • Paper, Video
  • Yin Cui et al., CVPR 2019
  • Keywords: Imbalanced Data
  • Presenter: Sunghoon Joo
  • [Top]

PR-204: Learning Deep Representations by Mutual Information Estimation and Maximization

  • Paper, Video
  • R Devon Hjelm et al., ICLR 2019
  • Keywords: Self-supervised Learning
  • Presenter: Seongok Ryu
  • [Top]

PR-205: A Closer Look at Few-shot Classification

  • Paper, Video
  • Wei-Yu Chen et al., ICLR 2019
  • Keywords: Few-shot Learning
  • Presenter: Taeoh Kim
  • [Top]

PR-206: PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud

  • Paper, Video
  • Shaoshuai Shi et al., CVPR 2019
  • Keywords: 3D Multi-view, 3D Detection
  • Presenter: Doyeop Lee
  • [Top]

PR-207: YOLOv3: An Incremental Improvement

  • Paper, Video
  • Joseph Redmon and Ali Farhadi, Arxiv 2018
  • Keywords: Detection
  • Presenter: Jinwon Lee
  • [Top]

PR-208: Unsupervised Visual Representation Learning Overview: Toward Self-Supervision

  • Paper1, Paper2, Paper3, Paper4, Paper5, Paper6, Video
  • Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks by Alexey Dosovitskiy at al. NIPS 2014
  • Unsupervised Visual Representation Learning by Context Prediction by Carl Doersch at al. ICCV 2015
  • Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles by Mehdi Noroozi and Paolo Favaro. ECCV 2016
  • Representation Learning by Learning to Count by Mehdi Noroozi et al. ICCV 2017
  • Multi-task Self-supervised Visual Learning by Carl Doersch and Andrew Zisserman, ICCV 2017
  • Unsupervised Representation Learning by Predicting Image Rotations by Spyros Gidaris et al. ICLR 2018
  • Keywords: Self-supervised Learning
  • Presenter: Hoseong Lee
  • [Top]

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.