AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Omni-Scale Feature Learning for Person Re-Identification

Kaiyang Zhou, Yongxin Yang, Andrea Cavallaro, Tao Xiang

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 1,197 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add unified aggregation gate instead of plain addition (ablation)OSNet T=4 · Market1501 (ablation)Rank-1 accuracy: 92.0 -> 93.6Improved
add unified aggregation gate instead of concatenation (ablation)OSNet T=4 · Market1501 (ablation)Rank-1 accuracy: 91.4 -> 93.6Improved
increase stream cardinality from T=1 to T=4 (ablation)OSNet · Market1501 (ablation)Rank-1 accuracy: 86.5 -> 93.6Improved
use streams of different depth (omni-scale) instead of same depth (ablation)OSNet T=4 · Market1501 (ablation)Rank-1 accuracy: 91.7 -> 93.6Improved
share one gate across streams instead of separate gates (ablation)OSNet T=4 · Market1501 (ablation)Rank-1 accuracy: 92.9 -> 93.6Improved
use channel-wise gates instead of stream-wise gates (ablation)OSNet T=4 · Market1501 (ablation)Rank-1 accuracy: 92.6 -> 93.6Improved
use dynamic input-dependent gates instead of static learned-and-fixed gates (ablation)OSNet T=4 · Market1501 (ablation)Rank-1 accuracy: 91.6 -> 93.6Improved
use factorised Lite 3x3 convolutions instead of full convolutions (ablation)OSNet T=4 · Market1501 (ablation)Rank-1 accuracy: 94.0 -> 93.6No clear effect
add unified AG with four streams instead of single scale (ablation)OSNet · CIFAR10error rate (%): 5.49 -> 4.41Improved
add deep mutual learning (model-1) (ablation)OSNet · Market1501 (training recipe, cosine annealing)mAP: 86.5 -> 87.2Improved
add triplet loss with weight 0.5 (ablation)OSNet · Market1501 (training recipe, cosine annealing)Rank-1 accuracy: 94.6 -> 95.5Improved
add entropy maximisation regulariser (lambda 0.1) (ablation)OSNet · Market1501 (training recipe, cosine annealing)Rank-1 accuracy: 94.6 -> 94.7No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy