MagnifierNet: Towards Semantic Adversary and Fusion for Person Re-identification

TL;DR

MagnifierNet is a novel triple-branch network that enhances person re-identification by magnifying details, learning from semantic-occluded samples, and selectively fusing features, achieving state-of-the-art results.

Contribution

The paper introduces MagnifierNet with a semantic adversarial branch, a semantic fusion branch, and a semantic diversity loss for improved person re-identification.

Findings

Achieved state-of-the-art performance on three benchmarks.

Improved mAP scores by 6% and 5% on CUHK03-L and CUHK03-D.

Effectively handles visually similar and occluded persons.

Abstract

Although person re-identification (ReID) has achieved significant improvement recently by enforcing part alignment, it is still a challenging task when it comes to distinguishing visually similar identities or identifying the occluded person. In these scenarios, magnifying details in each part features and selectively fusing them together may provide a feasible solution. In this work, we propose MagnifierNet, a triple-branch network which accurately mines details from whole to parts. Firstly, the holistic salient features are encoded by a global branch. Secondly, to enhance detailed representation for each semantic region, the "Semantic Adversarial Branch" is designed to learn from dynamically generated semantic-occluded samples during training. Meanwhile, we introduce "Semantic Fusion Branch" to filter out irrelevant noises by selectively fusing semantic region information sequentially. To further improve feature diversity, we introduce a novel loss function "Semantic Diversity Loss" to remove redundant overlaps across learned semantic representations. State-of-the-art performance has been achieved on three benchmarks by large margins. Specifically, the mAP score is improved by 6% and 5% on the most challenging CUHK03-L and CUHK03-D benchmarks.