Progressive Multi-stage Feature Mix for Person Re-Identification

TL;DR

This paper introduces a Progressive Multi-stage Feature Mix network (PMM) that enhances person re-identification by encouraging diverse feature learning through multi-stage classifiers and an innovative feature mixing technique, leading to improved accuracy.

Contribution

The paper proposes a novel PMM framework with multi-stage classifiers and A-Hard-Mix for more precise and diverse feature extraction in person re-ID tasks.

Findings

Significant performance boost on Market-1501, DukeMTMC-reID, CUHK03 datasets.

Effective in encouraging diverse feature attention across stages.

Outperforms existing methods in re-identification accuracy.

Abstract

Image features from a small local region often give strong evidence in person re-identification task. However, CNN suffers from paying too much attention on the most salient local areas, thus ignoring other discriminative clues, e.g., hair, shoes or logos on clothes. %BDB proposes to randomly drop one block in a batch to enlarge the high response areas. Although BDB has achieved remarkable results, there still room for improvement. In this work, we propose a Progressive Multi-stage feature Mix network (PMM), which enables the model to find out the more precise and diverse features in a progressive manner. Specifically, 1. to enforce the model to look for different clues in the image, we adopt a multi-stage classifier and expect that the model is able to focus on a complementary region in each stage. 2. we propose an Attentive feature Hard-Mix (A-Hard-Mix) to replace the salient feature blocks by the negative example in the current batch, whose label is different from the current sample. 3. extensive experiments have been carried out on reID datasets such as the Market-1501, DukeMTMC-reID and CUHK03, showing that the proposed method can boost the re-identification performance significantly.