AI Paper Atlas

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

OVL: One-View Learning for Human Retrieval

Wenjing Li, Zhongcheng Wu

AAAI 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 3 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
remove triplet loss (ablation)OVL framework · Market-1501 avg rank-1Rank-1: 59.5 -> 67.8Improved
add adversarial multi-view learning (AMVL) (ablation)OVL framework · Market-1501 avg rank-1Rank-1: 61.7 -> 67.8Improved
add adversarial unknown rejection learning (AURL) (ablation)OVL framework · Market-1501 avg rank-1Rank-1: 62.0 -> 67.8Improved
add AURL only to baseline (no AMVL) (ablation)Baseline · Market-1501 avg rank-1Rank-1: 41.9 -> 61.7Improved
AMVL instead of DANN (align to global target view)Baseline · Market-1501 avg rank-1Rank-1: 52.4 -> 62.0Improved
AMVL instead of ADDA with C-1 domain classifiersBaseline · Market-1501 avg rank-1Rank-1: 55.6 -> 62.0Improved
lambda_vi from 0.0 to 0.2 (ablation)OVL framework · Market-1501 (3rd view)Rank-1: 72.2 -> 78.1Improved
lambda_vi large (1.0) (ablation)OVL framework · Market-1501 (3rd view)Rank-1: 78.1 -> 73.5Hurt
lambda_un from 0.0 to 0.1 (ablation)OVL framework · Market-1501 (3rd view)Rank-1: 70.3 -> 78.1Improved
lambda_un increased to 0.5 (ablation)OVL framework · Market-1501 (3rd view)Rank-1: 78.1 -> 73.0Hurt
full method vs source-view-only baselineBaseline · DukeMTMC-reID avg rank-1Rank-1: 27.6 -> 52.1Improved
Ours vs domain adaptation method HHLOVL framework · Market-1501Rank-1: 62.2 -> 78.1Improved

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