Re-ID 2019 Review

Reference[原文]: Joselynzhao.top & 夏木青 | Re-ID 2019 Review

Train/Test on the same domain

Part-level features are effective.

pose and 3D information are beneficial

**Smothness in feature space is beneficial **

Unsupervised domain adaptation

Evolution in state-of-the art Performance

image-image translation benefits UDA; identity-preserving property benefits further

mining discriminative cues in the target domain improves the UDA accuracy

挖掘 区别性大的线索 提高 unsupervised domain adaptation accuracy.

Video re-id: frame-level weights are important

spatiotemporal attention network

person search

end-to-end framework

feature memory modeling is critical for end to end person search

separate person detector and re-identification seem to be a better choice.

Other problems

person re-id originates from person tracking; After years of study, person re-id features are improving tracking accuracies.

learning from synthetic data for person re-id
**Synthetic training data can help to initialize deep networds **

the diversity of synthetic data can help improve the generalization performance of re-ID models

合成数据的多样性……

Future research questions

1. is large-scale re-id really solved? what the performance will be if we scale up the gallery to 1 million or 10 million images? How to accelerate?
2. In unsupervised domain adaptation, person re-id is a open-set problem. what is its relationship with UDA in image classification?
3. What is the relationship between person detection and re-id? is it optimal to use re-id features in tracking?
4. How do environmental factors affect re-id?

感谢图片内容提供者：https://zhuanlan.zhihu.com/p/64004977