Style Interleaved Learning for Generalizable Person Re-identification

TL;DR

This paper introduces a style interleaved learning framework for person re-identification that enhances domain generalization by preventing overfitting to source domain styles through interleaved feature stylization and multiple forward-backward propagations.

Contribution

It proposes a novel style interleaved learning method with a new feature stylization approach to improve generalization in person ReID without target domain data.

Findings

Outperforms state-of-the-art on large-scale benchmarks

Improves generalization to unseen domains

Offers computational efficiency advantages

Abstract

Domain generalization (DG) for person re-identification (ReID) is a challenging problem, as access to target domain data is not permitted during the training process. Most existing DG ReID methods update the feature extractor and classifier parameters based on the same features. This common practice causes the model to overfit to existing feature styles in the source domain, resulting in sub-optimal generalization ability on target domains. To solve this problem, we propose a novel style interleaved learning (IL) framework. Unlike conventional learning strategies, IL incorporates two forward propagations and one backward propagation for each iteration. We employ the features of interleaved styles to update the feature extractor and classifiers using different forward propagations, which helps to prevent the model from overfitting to certain domain styles. To generate interleaved feature styles, we further propose a new feature stylization approach. It produces a wide range of meaningful styles that are both different and independent from the original styles in the source domain, which caters to the IL methodology. Extensive experimental results show that our model not only consistently outperforms state-of-the-art methods on large-scale benchmarks for DG ReID, but also has clear advantages in computational efficiency. The code is available at https://github.com/WentaoTan/Interleaved-Learning.