Dynamic Prototype Mask for Occluded Person Re-Identification

TL;DR

This paper introduces a Dynamic Prototype Mask (DPM) that automatically aligns occluded person features in an end-to-end trainable network, improving re-identification accuracy without relying on extra pre-trained models.

Contribution

The proposed DPM employs a hierarchical mask generator and head enrichment to enhance occluded person re-identification in an end-to-end framework, surpassing state-of-the-art methods.

Findings

DPM achieves superior performance on occluded and holistic benchmarks.

The hierarchical mask generator effectively aligns occluded features.

The head enrichment module improves feature diversity and representation.

Abstract

Although person re-identification has achieved an impressive improvement in recent years, the common occlusion case caused by different obstacles is still an unsettled issue in real application scenarios. Existing methods mainly address this issue by employing body clues provided by an extra network to distinguish the visible part. Nevertheless, the inevitable domain gap between the assistant model and the ReID datasets has highly increased the difficulty to obtain an effective and efficient model. To escape from the extra pre-trained networks and achieve an automatic alignment in an end-to-end trainable network, we propose a novel Dynamic Prototype Mask (DPM) based on two self-evident prior knowledge. Specifically, we first devise a Hierarchical Mask Generator which utilizes the hierarchical semantic to select the visible pattern space between the high-quality holistic prototype and the feature representation of the occluded input image. Under this condition, the occluded representation could be well aligned in a selected subspace spontaneously. Then, to enrich the feature representation of the high-quality holistic prototype and provide a more complete feature space, we introduce a Head Enrich Module to encourage different heads to aggregate different patterns representation in the whole image. Extensive experimental evaluations conducted on occluded and holistic person re-identification benchmarks demonstrate the superior performance of the DPM over the state-of-the-art methods. The code is released at https://github.com/stone96123/DPM.