Papers › Attribute De-biased Vision Transformer (AD-ViT) for Long-Term Person Re-identification

Attribute De-biased Vision Transformer (AD-ViT) for Long-Term Person Re-identification

29 Nov 2022IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) 2022 11archive 2025-07-28

Kyung Won Lee, Bhavin Jawade, Deen Mohan, Srirangaraj Setlur, and Venu Govindaraju

Person re-identification (re-ID) aims to retrieve images of the same identity from a gallery of person images across cameras and viewpoints. However, most works in person re-ID assume a short-term setting characterized by invariance in appearance. In contrast, a high visual variance can be frequently seen in a long-term setting due to changes in apparel and accessories, which makes the task more challenging. Therefore, learning identity-specific features agnostic of temporally variant features is crucial for robust long-term person Re-ID. To this end, we propose an Attribute De-biased Vision Transformer (AD-ViT) to provide direct supervision to learn identity-specific features. Specifically, we produce attribute labels for person instances and utilize them to guide our model to focus on identity features through gradient reversal. Our experiments on two longterm re-ID datasets - LTCC and NKUP show that the proposed work consistently outperforms current state-of-theart methods.

Paper PDF Code

Code

kyungwon213/AD_ViT pytorch 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

Attribute Person Identification Person Re-Identification Person Recognition Person Retrieval

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Person Re-Identification	LTCC	AD-ViT	Rank-1	-1	#13 of 13	Archive leaderboard	report
Person Re-Identification	LTCC	AD-ViT	mAP	-1	#13 of 13	Archive leaderboard	report
Person Re-Identification	LTCC	AD-ViT	Rank-1	-1	#13 of 13	Archive leaderboard	report
Person Re-Identification	LTCC	AD-ViT	mAP	-1	#13 of 13	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.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer Vision Transformer

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