Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification (ICCV 2019, Oral)
Implementation of the paper Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification, ICCV 2019 (Oral)
The SSG approach proposed in the paper is simple yet effective and achieves the state-of-arts on three re-ID datasets: Market1501, DukdMTMC and MSMT17.
Run
source_train.pyvia
python source_train.py \ --dataset \ --resume \ --data_dir \ --logs_dir
To replicate the results in the paper, you can download pre-trained models on Market1501, DukeMTMC and MSMT17 from GoogleDrive. There maybe some bugs in sourcetrain.py, please refer to DomainAdaptiveReID to obtained the pretrained model or just use the pretrained model provided by us. And you can find all models after adaptation from GoogleDrive. Our models can be trained with _PyTorch 0.4.1__ or PyTorch 1.0.
python selftraining.py \ --src_dataset \ --tgt_dataset \ --resume \ --iteration \ --data_dir \ --logs_dir \ --gpu-devices \ --num-split
Or just command
shell ./run.sh
python semitraining.py \ --src_dataset \ --tgt_dataset \ --resume \ --iteration \ --data_dir \ --logs_dir \ --gpu-devices \ --num-split \ --sample
| Source Dataset | Rank-1 | mAP | | :--- | :---: | :---: | | DukeMTMC | 82.6 | 70.5 | | Market1501 | 92.5 | 80.8 | | MSMT17 | 73.6 | 48.6 |
SRC --> TGT | Before Adaptation | Adaptation by SSG | Adaptation by SSG++ | |||
---|---|---|---|---|---|---|
Rank-1 | mAP | Rank-1 | mAP | Rank-1 | mAP | |
Market1501 --> DukeMTMC | 30.5 | 16.1 | 73.0 | 53.4 | 76.0 | 60.3 |
DukeMTMC --> Market1501 | 54.6 | 26.6 | 80.0 | 58.3 | 86.2 | 68.7 |
Market1501 --> MSMT17 | 8.6 | 2.7 | 31.6 | 13.2 | 37.6 | 16.6 |
DukeMTMC --> MSMT17 | 12.38 | 3.82 | 32.2 | 13.3 | 41.6 | 18.3 |
Our code is based on open-reid and DomainAdaptiveReID.
If you find the code helpful in your resarch or work, please cite the following paper.
@InProceedings{Fu_2019_ICCV, author = {Fu, Yang and Wei, Yunchao and Wang, Guanshuo and Zhou, Yuqian and Shi, Honghui and Huang, Thomas S.}, title = {Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification}, booktitle = {The IEEE International Conference on Computer Vision (ICCV)}, month = {October}, year = {2019} }