Occlusion-Guided Feature Purification Learning via Reinforced Knowledge Distillation for Occluded Person Re-Identification

TL;DR

This paper introduces OGFR, a novel occlusion-aware learning framework for person re-identification that uses reinforced knowledge distillation and a vision transformer to handle diverse occlusions and purify features.

Contribution

The paper proposes a new occlusion-guided feature purification method with reinforced knowledge distillation and an occlusion-aware transformer for robust occluded person re-identification.

Findings

Effective handling of diverse occlusion scenarios.

Improved feature robustness and discrimination.

Superior performance on occluded person re-ID benchmarks.

Abstract

Occluded person re-identification aims to retrieve holistic images based on occluded ones. Existing methods often rely on aligning visible body parts, applying occlusion augmentation, or complementing missing semantics using holistic images. However, they face challenges in handling diverse occlusion scenarios not seen during training and the issue of feature contamination from holistic images. To address these limitations, we propose Occlusion-Guided Feature Purification Learning via Reinforced Knowledge Distillation (OGFR), which simultaneously mitigates these challenges. OGFR adopts a teacher-student distillation architecture that effectively incorporates diverse occlusion patterns into feature representation while transferring the purified discriminative holistic knowledge from the holistic to the occluded branch through reinforced knowledge distillation. Specifically, an Occlusion-Aware Vision Transformer is designed to leverage learnable occlusion pattern embeddings to explicitly model such diverse occlusion types, thereby guiding occlusion-aware robust feature representation. Moreover, we devise a Feature Erasing and Purification Module within the holistic branch, in which an agent is employed to identify low-quality patch tokens of holistic images that contain noisy negative information via deep reinforcement learning, and substitute these patch tokens with learnable embedding tokens to avoid feature contamination and further excavate identity-related discriminative clues. Afterward, with the assistance of knowledge distillation, the student branch effectively absorbs the purified holistic knowledge to precisely learn robust representation regardless of the interference of occlusions.