Papers › Person Re-identification with Bias-controlled Adversarial Training

Person Re-identification with Bias-controlled Adversarial Training

30 Mar 2019arXiv:1904.00244archive 2025-07-28

Sara Iodice, Krystian Mikolajczyk

Inspired by the effectiveness of adversarial training in the area of Generative Adversarial Networks we present a new approach for learning feature representations in person re-identification. We investigate different types of bias that typically occur in re-ID scenarios, i.e., pose, body part and camera view, and propose a general approach to address them. We introduce an adversarial strategy for controlling bias, named Bias-controlled Adversarial framework (BCA), with two complementary branches to reduce or to enhance bias-related features. The results and comparison to the state of the art on different benchmarks show that our framework is an effective strategy for person re-identification. The performance improvements are in both full and partial views of persons.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Person Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Re-Identification DukeMTMC-reID Bias-controlled Adversarial Training Rank-1 85.2 #58 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID Bias-controlled Adversarial Training mAP 74.8 #58 of 94 Archive leaderboard report
Person Re-Identification Market-1501 Bias-controlled Adversarial Training Rank-1 93.1 #87 of 135 Archive leaderboard report
Person Re-Identification Market-1501 Bias-controlled Adversarial Training mAP 89.3 #87 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