AI Paper Atlas

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

Learning Invariance From Generated Variance for Unsupervised Person Re-Identification

Hao Chen, Yaohui Wang, Benoit Lagadec, Antitza Dantcheva, François Brémond

TPAMI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification · 46 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 D-Mixup on top of mesh rotation (ablation)GCL+ · Market-1501 (fully unsupervised)mAP: 63.8 -> 66.3Improved
replace multiple traditional augmentations with mesh-guided rotation (ablation)GCL+ contrastive module · Market-1501 (fully unsupervised)mAP: 58.2 -> 63.8Improved
use D-Mixup instead of image-level Mixup (ablation)GCL+ · Market-1501 (fully unsupervised)mAP: 65.9 -> 66.3Improved
use D-Mixup instead of feature-level Mixup (ablation)GCL+ · Market-1501 (fully unsupervised)mAP: 66.1 -> 66.3Improved
add traditional multi augmentation in contrastive module (ablation)JVTC baseline · Market-1501 (fully unsupervised)mAP: 47.2 -> 58.2Improved
add view-invariant loss L_vi' (ablation)GCL+ · Duke->Market (UDA)mAP: 61.6 -> 69.1Improved
add view-invariant loss L_vi'' (ablation)GCL+ · Duke->Market (UDA)mAP: 69.1 -> 72.5Improved
add prototype loss L_proto (ablation)GCL+ · Duke->Market (UDA)mAP: 72.5 -> 72.8Improved
add mixed prototype loss L_mix (ablation)GCL+ · Duke->Market (UDA)mAP: 72.8 -> 74.4Improved
rotate one mesh instead of switching 2D gray images (ablation)GCL+ · Duke->Market (UDA)mAP: 60.1 -> 74.4Improved
rotate one mesh instead of switching two meshes (ablation)GCL+ · Duke->Market (UDA)mAP: 74.2 -> 74.4No clear effect
raise DBSCAN distance threshold from 0.5 to 0.6 (ablation)GCL+ · Duke->Market (UDA)mAP: 74.4 -> 72.4Hurt

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