Second-order Non-local Attention Networks for Person Re-identification

TL;DR

This paper introduces a second-order non-local attention mechanism combined with DropBlock to improve person re-identification by modeling long-range feature relationships, achieving state-of-the-art results on multiple datasets.

Contribution

The paper presents a novel second-order non-local attention mechanism for person re-ID, directly modeling long-range relationships, and integrates it with DropBlock for enhanced performance.

Findings

Achieves comparable or superior results to state-of-the-art methods on Market1501, CUHK03, and DukeMTMC-reID datasets.

Effectively models long-range dependencies in feature maps for person re-identification.

Improves discriminative feature learning through the combination of second-order attention and DropBlock.

Abstract

Recent efforts have shown promising results for person re-identification by designing part-based architectures to allow a neural network to learn discriminative representations from semantically coherent parts. Some efforts use soft attention to reallocate distant outliers to their most similar parts, while others adjust part granularity to incorporate more distant positions for learning the relationships. Others seek to generalize part-based methods by introducing a dropout mechanism on consecutive regions of the feature map to enhance distant region relationships. However, only few prior efforts model the distant or non-local positions of the feature map directly for the person re-ID task. In this paper, we propose a novel attention mechanism to directly model long-range relationships via second-order feature statistics. When combined with a generalized DropBlock module, our method performs equally to or better than state-of-the-art results for mainstream person re-identification datasets, including Market1501, CUHK03, and DukeMTMC-reID.