AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework Using Self-Supervised Multi-Task Learning

Linhao Qu, Shaolei Liu, Manning Wang, Zhijian Song

AAAI 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Pretext-task visual pre-training · 179 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 TransBlock (CNN+transformer encoder) to the encoder, with self-supervised tasks (ablation)TransMEF · MEF benchmark (100 pairs), 20% training datafusion objective metricsImproved
add TransBlock to the encoder, without self-supervised tasks (ablation)TransMEF · MEF benchmark (100 pairs), 20% training datafusion objective metricsImproved
use each single self-supervised reconstruction task alone (Gamma, Fourier, or region shuffling) (ablation)TransMEF · MEF benchmark, 20% training datafusion objective metricsImproved
conduct all three self-supervised tasks simultaneously via multi-task learning instead of individually (ablation)TransMEF · MEF benchmark, 20% training datafusion objective metricsImproved
use TransBlock encoder instead of CNN-only encoder for image reconstruction (ablation)TransMEF encoder · image reconstruction examplesMSE, SSIM, PSNRImproved
TransMEF vs 11 traditional and deep MEF methodsTransMEF · MEF benchmark, 12 objective metrics12 fusion metrics: best on nine of 12 metricsImproved

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