RepPoints

by microsoft

microsoft /RepPoints

Represent Visual Objects by Point Sets

479 Stars 60 Forks Last release: Not found MIT License 14 Commits 0 Releases

Available items

No Items, yet!

The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:

RepPoints: Point Set Representation for Object Detection

By Ze Yang, Shaohui Liu, and Han Hu.

We provide code support and configuration files to reproduce the results in the paper for "RepPoints: Point Set Representation for Object Detection" on COCO object detection. Our code is based on mmdetection, which is a clean open-sourced project for benchmarking object detection methods.

Introduction

RepPoints, initially described in arXiv, is a new representation method for visual objects, on which visual understanding tasks are typically centered. Visual object representation, aiming at both geometric description and appearance feature extraction, is conventionally achieved by

bounding box + RoIPool (RoIAlign)
. The bounding box representation is convenient to use; however, it provides only a rectangular localization of objects that lacks geometric precision and may consequently degrade feature quality. Our new representation, RepPoints, models objects by a
point set
instead of a
bounding box
, which learns to adaptively position themselves over an object in a manner that circumscribes the object’s
spatial extent
and enables
semantically aligned feature extraction
. This richer and more flexible representation maintains the convenience of bounding boxes while facilitating various visual understanding applications. This repo demonstrated the effectiveness of RepPoints for COCO object detection.

Another feature of this repo is the demonstration of an

anchor-free detector
, which can be as effective as state-of-the-art anchor-based detection methods. The anchor-free detector can utilize either
bounding box
or
RepPoints
as the basic object representation.

Learning RepPoints in Object Detection.

Usage

a. Clone the repo:

git clone --recursive https://github.com/microsoft/RepPoints
b. Download the COCO detection dataset, copy RepPoints src into mmdetection and install mmdetection.
sh ./init.sh
c. Run experiments with a speicific configuration file:
./mmdetection/tools/dist_train.sh ${path-to-cfg-file} ${num_gpu} --validate
We give one example here:
./mmdetection/tools/dist_train.sh ./configs/reppoints_moment_r101_fpn_2x_mt.py 8 --validate

Citing RepPoints

@inproceedings{yang2019reppoints,
  title={RepPoints: Point Set Representation for Object Detection},
  author={Yang, Ze and Liu, Shaohui and Hu, Han and Wang, Liwei and Lin, Stephen},
  booktitle={The IEEE International Conference on Computer Vision (ICCV)},
  month={Oct},
  year={2019}
}

Results and models

The results on COCO 2017val are shown in the table below.

| Method | Backbone | Anchor | convert func | Lr schd | box AP | Download | | :----: | :------: | :-------: | :------: | :-----: | :----: | :------: | | BBox | R-50-FPN | single | - | 1x | 36.3|model | | BBox | R-50-FPN | none | - | 1x | 37.3| model | | RepPoints | R-50-FPN | none | partial MinMax | 1x | 38.1| model | | RepPoints | R-50-FPN | none | MinMax | 1x | 38.2| model | | RepPoints | R-50-FPN | none | moment | 1x | 38.2| model | | RepPoints | R-50-FPN | none | moment | 2x | 38.6| model | | RepPoints | R-50-FPN | none | moment | 2x (ms train) | 40.8| model | | RepPoints | R-50-FPN | none | moment | 2x (ms train&ms test) | 42.2| | | RepPoints | R-101-FPN | none | moment | 2x | 40.3| model | | RepPoints | R-101-FPN | none | moment | 2x (ms train) | 42.3| model | | RepPoints | R-101-FPN | none | moment | 2x (ms train&ms test) | 44.1| | | RepPoints | R-101-FPN-DCN | none | moment | 2x | 43.0| model | | RepPoints | R-101-FPN-DCN | none | moment | 2x (ms train) | 44.8| model | | RepPoints | R-101-FPN-DCN | none | moment | 2x (ms train&ms test) | 46.4| | | RepPoints | X-101-FPN-DCN | none | moment | 2x | 44.5| model | | RepPoints | X-101-FPN-DCN | none | moment | 2x (ms train) | 45.6| model | | RepPoints | X-101-FPN-DCN | none | moment | 2x (ms train&ms test) | 46.8| |

Notes:

  • R-xx
    ,
    X-xx
    denote the ResNet and ResNeXt architectures, respectively.
  • DCN
    denotes replacing 3x3 conv with the 3x3 deformable convolution in
    c3-c5
    stages of backbone.
  • none
    in the
    anchor
    column means 2-d
    center point
    (x,y) is used to represent the initial object hypothesis.
    single
    denotes one 4-d anchor box (x,y,w,h) with IoU based label assign criterion is adopted.
  • moment
    ,
    partial MinMax
    ,
    MinMax
    in the
    convert func
    column are three functions to convert a point set to a pseudo box.
  • ms
    denotes multi-scale training or multi-scale test.
  • Note the results here are slightly different from those reported in the paper, due to framework change. While the original paper uses an MXNet implementation, we re-implement the method in PyTorch based on mmdetection.

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.microsoft.com.

When you submit a pull request, a CLA-bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., label, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.

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.