FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification

TL;DR

FD-GAN is a novel pose-guided generative adversarial network that learns robust, pose-unrelated person features for re-identification without extra pose info during testing, achieving state-of-the-art results.

Contribution

It introduces a pose-guided feature distilling framework with novel discriminators and a same-pose loss, eliminating the need for auxiliary pose data at inference.

Findings

Achieves state-of-the-art performance on three reID datasets.

Learns pose-unrelated features without extra pose information during testing.

Demonstrates robustness and effectiveness in person re-identification.

Abstract

Person re-identification (reID) is an important task that requires to retrieve a person's images from an image dataset, given one image of the person of interest. For learning robust person features, the pose variation of person images is one of the key challenges. Existing works targeting the problem either perform human alignment, or learn human-region-based representations. Extra pose information and computational cost is generally required for inference. To solve this issue, a Feature Distilling Generative Adversarial Network (FD-GAN) is proposed for learning identity-related and pose-unrelated representations. It is a novel framework based on a Siamese structure with multiple novel discriminators on human poses and identities. In addition to the discriminators, a novel same-pose loss is also integrated, which requires appearance of a same person's generated images to be similar. After learning pose-unrelated person features with pose guidance, no auxiliary pose information and additional computational cost is required during testing. Our proposed FD-GAN achieves state-of-the-art performance on three person reID datasets, which demonstrates that the effectiveness and robust feature distilling capability of the proposed FD-GAN.