Learning Disentangled Representation for Robust Person Re-identification

NeurIPS 2019  ·  Chanho Eom, Bumsub Ham ·

We address the problem of person re-identification (reID), that is, retrieving person images from a large dataset, given a query image of the person of interest. A key challenge is to learn person representations robust to intra-class variations, as different persons can have the same attribute and the same person's appearance looks different with viewpoint changes. Recent reID methods focus on learning discriminative features but robust to only a particular factor of variations (e.g., human pose), which requires corresponding supervisory signals (e.g., pose annotations). To tackle this problem, we propose to disentangle identity-related and -unrelated features from person images. Identity-related features contain information useful for specifying a particular person (e.g., clothing), while identity-unrelated ones hold other factors (e.g., human pose, scale changes). To this end, we introduce a new generative adversarial network, dubbed \emph{identity shuffle GAN} (IS-GAN), that factorizes these features using identification labels without any auxiliary information. We also propose an identity-shuffling technique to regularize the disentangled features. Experimental results demonstrate the effectiveness of IS-GAN, significantly outperforming the state of the art on standard reID benchmarks including the Market-1501, CUHK03 and DukeMTMC-reID. Our code and models are available online: https://cvlab-yonsei.github.io/projects/ISGAN/.

PDF Abstract NeurIPS 2019 PDF NeurIPS 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Person Re-Identification DukeMTMC-reID IS-GAN Rank-1 90.0 # 34
mAP 79.5 # 43
Person Re-Identification Market-1501 IS-GAN Rank-1 95.2 # 54
mAP 87.1 # 67

Methods


No methods listed for this paper. Add relevant methods here