Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification

TL;DR

This paper introduces PGFL-KD, a pose-guided feature learning network with knowledge distillation that improves occluded person re-identification by focusing on visible body parts and semantics without relying on pose information during testing.

Contribution

The paper proposes a novel network that uses pose-guided branches and knowledge distillation to enhance feature learning for occluded person ReID, eliminating pose dependency at test time.

Findings

Effective in occluded, partial, and holistic ReID tasks.

Improves feature alignment and robustness to occlusion.

Achieves state-of-the-art performance on benchmark datasets.

Abstract

Occluded person re-identification (ReID) aims to match person images with occlusion. It is fundamentally challenging because of the serious occlusion which aggravates the misalignment problem between images. At the cost of incorporating a pose estimator, many works introduce pose information to alleviate the misalignment in both training and testing. To achieve high accuracy while preserving low inference complexity, we propose a network named Pose-Guided Feature Learning with Knowledge Distillation (PGFL-KD), where the pose information is exploited to regularize the learning of semantics aligned features but is discarded in testing. PGFL-KD consists of a main branch (MB), and two pose-guided branches, \ieno, a foreground-enhanced branch (FEB), and a body part semantics aligned branch (SAB). The FEB intends to emphasise the features of visible body parts while excluding the interference of obstructions and background (\ieno, foreground feature alignment). The SAB encourages different channel groups to focus on different body parts to have body part semantics aligned representation. To get rid of the dependency on pose information when testing, we regularize the MB to learn the merits of the FEB and SAB through knowledge distillation and interaction-based training. Extensive experiments on occluded, partial, and holistic ReID tasks show the effectiveness of our proposed network.