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

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

6 Oct 2018NeurIPS 2018 12arXiv:1810.02936archive 2025-07-28

Yixiao Ge, Zhuowan Li, Haiyu Zhao, Guojun Yin, Shuai Yi, Xiaogang Wang, Hongsheng Li

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.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

yxgeee/FD-GAN officialmentioned in papermentioned on GitHubpytorch report
NVlabs/DG-Net pytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Person Re-Identification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Re-Identification CUHK03 FD-GAN MAP 91.3 #3 of 19 Archive leaderboard report
Person Re-Identification CUHK03 FD-GAN Rank-1 92.6 #3 of 19 Archive leaderboard report
Person Re-Identification DukeMTMC-reID FD-GAN Rank-1 80.0 #71 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID FD-GAN mAP 64.5 #71 of 94 Archive leaderboard report
Person Re-Identification Market-1501 FD-GAN Rank-1 90.5 #92 of 135 Archive leaderboard report
Person Re-Identification Market-1501 FD-GAN mAP 77.7 #92 of 135 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections