Papers › Person Re-identification with Bias-controlled Adversarial Training
Person Re-identification with Bias-controlled Adversarial Training
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.
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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