Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Deep Learning for Person Re-identification: A Survey and Outlook
| Date | Stars |
|---|---|
| 2026-07-31 | 754 |
| 2026-08-02 | 754 |
| 2026-08-06 | 754 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# IJCV 2024: Transformer-based ReID Survey
Transformer for Object Re-Identification: A Survey. [arXiv](https://arxiv.org/abs/2401.06960v2)
- An implementation of UntransReID for unsupervised Re-ID is [HERE](https://github.com/whucsy/ReID-Survey/tree/master/Transformer-ReID-Survey/UnTransReID_USL_ReID).
- An implementation of UntransReID for cross-modality visible-infrared unsupervised Re-ID is [HERE](https://github.com/whucsy/ReID-Survey/tree/master/Transformer-ReID-Survey/UnTransReID_VI_ReID).
- An implementation of the unified experimental standard for animal Re-ID is [HERE](https://github.com/whucsy/ReID-Survey/tree/master/Transformer-ReID-Survey/Animal-Re-ID-main).
## Highlights
- An in-depth analysis of Transformer's strengths, highlighting its impact across four key Re-ID directions: image/video-based, limited data/annotations, cross-modal, and special scenarios.
- A new Transformer-based unsupervised baseline, UntransReID, achieving state-of-the-art performance on both single/cross modal Re-ID.
- A unified experimental standard for animal Re-ID, designed to address its unique challenges and evaluate the potential of Transformer-based approaches.
### Citation
Please kindly cite this paper in your publications if it helps your research:
```
@article{ye2024transformer,
title={Transformer for Object Re-Identification: A Survey},
author={Ye, Mang and Chen, Shuoyi and Li, Chenyue and Zheng, Wei-Shi and Crandall, David and Du, Bo},
journal={arXiv preprint arXiv:2401.06960},
year={2024}
}
```
# TPAMI 2021 ReID-Survey with a Powerful AGW Baseline
Deep Learning for Person Re-identification: A Survey and Outlook. PDF with supplementary materials. [arXiv](https://arxiv.org/abs/2001.04193v2)
- An implementation of AGW for cross-modality visible-infrared Re-ID is [HERE](https://github.com/mangye16/Cross-Modal-Re-ID-baseline).
- An implementation of AGW for video Re-ID is [HERE](https://github.com/mangye16/ReID-Survey/tree/master/video-reid-AWG)
- An implementation of AGW for partial Re-ID is [HERE](https://github.com/mangye16/ReID-Survey/blob/master/Experiment-AGW-partial.sh).
A simplified introduction in Chinese on [知乎](https://zhuanlan.zhihu.com/p/342249413).
## Highlights
- A comprehensive survey with in-depth analysis for closed- and open-world person Re-ID in recent years (2016-2020).
- A new evaluation metric, namely mean Inverse Negative Penalty (mINP), which measures the ability to find the hardest correct match.
- A new AGW baseline with non-local Attention block, Generalized mean pooling and Weighted regularization triplet. It acheieves competitive performance on FOUR challenging Re-ID tasks, including single-modality image-based Re-ID, video-based Re-ID, Partial Re-ID and [cross-modality](https://github.com/mangye16/Cross-Modal-Re-ID-baseline) Re-ID.
## AGW on Single-Modality Image Re-ID with mINP
#### DukeMTMC dataset
|Method | Pretrained| Rank@1 | mAP | mINP | Model| Paper
| -------- | ----- | ----- | ----- | ----- |------|------------------------|
|BagTricks | ImageNet | 86.4% | 76.4%| 40.7% |[Code](https://github.com/michuanhaohao/reid-strong-baseline) |Bag of Tricks and A Strong Baseline for Deep Person Re-identification. In ArXiv 19. [PDF](https://arxiv.org/abs/1903.07071)|
|ABD-Net | ImageNet | 89.0% | 78.6%| 42.1% | [Code](https://github.com/TAMU-VITA/ABD-Net) |ABD-Net: Attentive but Diverse Person Re-Identification. In ICCV 19. [PDF](https://arxiv.org/abs/1908.01114)|
|AGW | ImageNet | 89.0% | 79.6% | 45.7% | [GoogleDrive](https://drive.google.com/open?id=1q3n_acTe-vaEeIpkJG2k0HqSEZrTJoGA)| Deep Learning for Person Re-identification: A Survey and Outlook |
#### Market-1501 dataset
|Method | Pretrained| Rank@1 | mAP | mINP | Model| Paper
| -------- | ----- | ----- | ----- | ----- |------|------|
|BagTricks | ImageNet | 94.5% | 85.9%| 59.4% |[Code](https://github.com/michuanhaohao/reid-strong-baseline) |Bag of Tricks and A Strong Excerpt of 7,777 characters
Read on GitHub
23
5
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:19bd8d9281453194, topic:deep-learning