AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Semi-Supervised High Dynamic Range Image Reconstructing via Bi-Level Uncertain Area Masking

Wei Jiang, Jiahao Cui, Yizheng Wu, Zhan Peng, Zhiyu Pan, Zhiguo Cao

AAAI 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Pseudo-labeling for specialized tasks · 0 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 vanilla mean teacher without rectifying pseudo labels (ablation)GFHDR · Kalantari 6.7% GTsPSNR-mu: 42.7220 -> 42.6509No clear effect
add uncertainty loss producing uncertainty scores (ablation)BL+MT · Kalantari 6.7% GTsPSNR-mu: 42.6509 -> 42.8893No clear effect
add patch-level masking (ablation)BL+MT+L^k · Kalantari 6.7% GTsPSNR-mu: 42.8893 -> 43.3528Improved
add pixel-level masking (ablation)BL+MT+L^k · Kalantari 6.7% GTsPSNR-mu: 42.8893 -> 43.2513Improved
use both patch- and pixel-level masking (ablation)BL+MT+L^k · Kalantari 6.7% GTsPSNR-mu: 42.8893 -> 43.4787Improved
add strong augmentations for pseudo-labeled training (ablation)BL+MT+L^k+PaM+PiM · Kalantari 6.7% GTsPSNR-mu: 43.4787 -> 44.0378Improved
use judge-network uncertainty instead of SMAE APSS scoring (ablation)MT framework · Kalantari 6.7% GTsPSNR-mu: 42.7956 -> 44.0378Improved
use mean-teacher masking strategy instead of FSHDR synthetic pseudo-labels (ablation)BL · Kalantari 6.7% GTsPSNR-mu: 43.5640 -> 44.0378Improved
apply semi-supervised method over GFHDR baselineGFHDR · Kalantari 6.7% GTsPSNR-mu: 42.72 -> 44.15Improved
increase labeled data from 6.7% to 27.0%Ours · KalantariPSNR-mu: 44.15 -> 44.21No clear effect
use semi-supervised method with 6.7% labels vs supervised GFHDR with 100% labelsOurs · KalantariPSNR-mu: 44.32 -> 44.15Improved
apply semi-supervised method over GFHDR on Hu datasetGFHDR · HuPSNR-mu: 42.97±0.17 -> 45.10±0.25Improved

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