AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID

Yixiao Ge, Feng Zhu, Dapeng Chen, Rui Zhao, hongsheng Li

NeurIPS 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 338 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
Use hybrid source-class, target-cluster, and target-instance supervision with self-paced clustering (ablation)SpCL · MSMT17→Market-1501mAP: 69.2 -> 77.5Improved
Add self-paced learning to target cluster training (ablation)Source classes + target clusters · MSMT17→Market-1501mAP: 28.9 -> 69.2Improved
Use each target instance as a distinct class rather than clustering instances (ablation)UDA training with source classes · MSMT17→Market-1501mAP: 25.3 -> 4.9Hurt
Include target-domain supervision alongside source classes (ablation)Source-class-only training · MSMT17→Market-1501mAP: 25.3 -> 77.5Improved
Use source class centroids instead of learnable source weights (ablation)SpCL · MSMT17→Market-1501mAP: 77.5 -> 70.7Hurt
Remove unified contrast across supervision types (ablation)SpCL · MSMT17→Market-1501mAP: 77.5 -> 68.8Hurt
Use independence and compactness reliability criteria (ablation)SpCL self-paced clustering · MSMT17→Market-1501mAP: 74.5 -> 77.5Improved
Use independence and compactness reliability criteria (ablation)SpCL without source data · Market-1501mAP: 68.2 -> 73.1Improved
Apply self-paced learning to agglomerative clustering (ablation)Unsupervised SpCL · Market-1501mAP: 70.4 -> 75.2Improved
Replace the reliability criterion with HDBSCAN (ablation)Unsupervised SpCL · Market-1501mAP: 73.1 -> 71.7Hurt
Replace ResNet-50 with IBN-ResNet (ablation)SpCL · Person re-ID adaptation tasksmAPMixed
Train jointly with unlabeled target data while retaining source-domain supervisionSource-domain encoder · MSMT17 source evaluationmAP: 84.7 -> 86.8Improved

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