Papers › Robust Re-Identification by Multiple Views Knowledge Distillation

Robust Re-Identification by Multiple Views Knowledge Distillation

8 Jul 2020ECCV 2020 8arXiv:2007.04174archive 2025-07-28

Angelo Porrello, Luca Bergamini, Simone Calderara

To achieve robustness in Re-Identification, standard methods leverage tracking information in a Video-To-Video fashion. However, these solutions face a large drop in performance for single image queries (e.g., Image-To-Video setting). Recent works address this severe degradation by transferring temporal information from a Video-based network to an Image-based one. In this work, we devise a training strategy that allows the transfer of a superior knowledge, arising from a set of views depicting the target object. Our proposal - Views Knowledge Distillation (VKD) - pins this visual variety as a supervision signal within a teacher-student framework, where the teacher educates a student who observes fewer views. As a result, the student outperforms not only its teacher but also the current state-of-the-art in Image-To-Video by a wide margin (6.3% mAP on MARS, 8.6% on Duke-Video-ReId and 5% on VeRi-776). A thorough analysis - on Person, Vehicle and Animal Re-ID - investigates the properties of VKD from a qualitatively and quantitatively perspective. Code is available at https://github.com/aimagelab/VKD.

Paper PDF Conference PDF Code

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

Code

aimagelab/VKD officialmentioned in papermentioned on GitHubpytorch 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

Knowledge Distillation Person Re-Identification Vehicle Re-Identification Video-Based Person Re-Identification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Person Re-Identification	MARS	VKD (ResVKD-50bam)	Rank-1	89.4	#9 of 21	Archive leaderboard	report
Person Re-Identification	MARS	VKD (ResVKD-50bam)	Rank-5	96.8	#9 of 21	Archive leaderboard	report
Person Re-Identification	MARS	VKD (ResVKD-50bam)	mAP	83.1	#9 of 21	Archive leaderboard	report
Vehicle Re-Identification	VeRi	VKD (ResVKD-50)	mAP	82.2	#2 of 2	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

1x1 Convolution Average Pooling Batch Normalization Bottleneck Residual Block Convolution Global Average Pooling Kaiming Initialization Knowledge Distillation Max Pooling ReLU Residual Block Residual Connection

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