AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

HLA-Face: Joint High-Low Adaptation for Low Light Face Detection

Wenjing Wang, Wenhan Yang, Jiaying Liu

CVPR 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 94 citations (OpenAlex)

Check 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 weak brightening with strong brightening (ablation)HLA-Face · DARK FACE testmAP (%): 38.3 -> 39.1Improved
Use jigsaw rather than rotation self-supervision alone (ablation)HLA-Face · DARK FACE testmAP (%): 22.7 -> 26.9Improved
Add rotation prediction to jigsaw self-supervision (ablation)HLA-Face · DARK FACE testmAP (%): 26.9 -> 25.3Hurt
Add cross-domain contrastive learning between H and D(H) (ablation)Strong-brightening HLA-Face · DARK FACE testmAP (%): 39.1 -> 40.9Improved
Use contrastive learning on H only instead of cross-domain contrastive learning (ablation)Strong-brightening HLA-Face · DARK FACE testmAP (%): 39.1 -> 38.2Hurt
Add pseudo labels on D(H) (ablation)Strong-brightening HLA-Face · DARK FACE testmAP (%): 39.1 -> 40.2Improved
Add jigsaw adaptation between E(L) and H (ablation)Strong-brightening HLA-Face · DARK FACE testmAP (%): 39.1 -> 40.2Improved
Add single-domain contrastive learning on E(L) (ablation)Strong-brightening HLA-Face with cross-domain contrastive learning · DARK FACE testmAP (%): 40.9 -> 41.1Improved
Combine jigsaw, cross-domain contrastive, and E(L) contrastive learning (ablation)HLA-Face · DARK FACE testmAP (%): 41.1 -> 41.4Improved
Add DSFD pyramid multi-scale testing (ablation)HLA-Face · DARK FACE testmAP (%): 41.4 -> 44.4Improved
Use HLA-Face without DARK FACE training labels instead of DSFDDSFD · DARK FACE testmAP (%): 16.1 -> 44.4Improved
Use CycleGAN-generated data with pseudo-label fine-tuning rather than CycleGAN-generated data aloneDSFD · DARK FACE testmAP (%): 31.9% to 35.1%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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