Bias Eliminate Domain Adaptive Pedestrian Re-identification [Technique Report]
This repo contains our code for VisDA2020 challenge at ECCV workshop.
This work mainly solve the domain adaptive pedestrian re-identification problem by eliminishing the bias from inter-domain gap and intra-domain camera difference.
This project is mainly based on reid-strong-baseline.
- Clone the repo
git clone https://github.com/vimar-gu/Bias-Eliminate-DA-ReID.git - Install dependencies:
- pytorch >= 1.0.0
- python >= 3.5
- torchvision
- yacs
- Prepare dataset. It can be obtained from Simon4Yan/VisDA2020.
- We use ResNet-ibn and HRNet as backbones. ImageNet pretrained models can be downloaded in here and here.
If you want to reproduce our results, please refer to [VisDA.md]
The performance on VisDA2020 validation dataset
| Method | mAP | Rank-1 | Rank-5 | Rank-10 |
|---|---|---|---|---|
| Basline | 30.7 | 59.7 | 77.5 | 83.3 |
| + Domain Adaptation | 44.9 | 75.3 | 86.7 | 91.0 |
| + Finetuning | 48.6 | 79.8 | 88.3 | 91.5 |
| + Post Processing | 70.9 | 86.5 | 92.8 | 94.4 |
The models can be downloaded from:
- ResNet50-ibn-a: Google Drive
- ResNet101-ibn-a: Google Drive
- ResNet50-ibn-b: Google Drive
- HRNetv2-w18: Google Drive
- ResNet50-ibn-a-large: Google Drive
- ResNet101-ibn-a-large: Google Drive
- ResNet50-ibn-b-large: Google Drive
- HRNetv2-w18-large: Google Drive
The camera models can be downloaded from:
- Camera(ResNet101): Google Drive
- Camera(ResNet152): Google Drive
- Camera(ResNet101-ibn-a): Google Drive
- Camera(HRNetv2-w18): Google Drive
- By our experience, there can be a large fluctuation of validation scores which are not completely positive correlated to the scores on testing set.
- We have fixed the random seed in the updates. But there might still be some difference due to environment.
- Multiple camera models in the testing phase may boost the performance by a little bit.