AI Paper Atlas

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

Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization

Zijie Zhuang, Longhui Wei, Lingxi Xie, Tianyu Zhang, Hengheng Zhang, Haozhe Wu, Haizhou Ai, Qi Tian

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification · 203 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
replace dataset-based formulation with camera-based batch normalization (CBN)ReID ResNet-50 baseline · Market to Duke direct transferRank-1: 37.0 -> 58.7Improved
replace dataset-based formulation with CBNReID ResNet-50 baseline · Duke to Market direct transferRank-1: 53.2 -> 72.7Improved
replace dataset-based formulation with CBNReID ResNet-50 baseline · Duke fully-supervisedRank-1: 81.5 -> 82.5Improved
integrate CBN into BoT* (Random Erasing disabled)BoT* · Market fully-supervisedRank-1: 93.6 -> 94.3Improved
integrate CBN into ECN domain adaptationECN · Duke to MarketRank-1: 75.1 -> 81.7Improved
add inter-camera annotations (fully versus weakly supervised) under CBNCBN ReID · Market train, Market and MSMT testRank-1: 83.3 -> 91.3 (Market); 26.8 -> 25.3 (MSMT)Mixed
use CBN instead of conventional formulation for Data-Free incremental learning (length 2)baseline ReID · Market first dataset retentionRank-1: 82.2% -> 88.3%Improved
use CBN instead of conventional formulation with Replay (length 3)baseline ReID · MSMT first dataset retentionmAP: 60.9% -> 76.0%Improved
add CBN at training time on top of CBN at test time (ablation)BN-trained model with CBN test · Duke to MarketRank-1: 69.5 -> 72.7Improved
replace AdaBN test-set alignment with CBN camera-wise alignment at test (ablation)BN-trained model · Duke to MarketRank-1: 55.8 -> 69.5Improved
replace BN with IBN (ablation)ReID baseline · Duke to Duke and Duke to MarketRank-1: 81.5 -> 77.6 (Duke); 53.2 -> 61.7 (Market)Mixed
estimate camera statistics from 50 batches instead of 1 (ablation)CBN · Market to DukemAP: 37.34 -> 38.21Improved

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