AI Paper Atlas

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

DuGI-MAE: Improving Infrared Mask Autoencoders via Dual-Domain Guidance

Yinghui Xing, Xiaoting Su, Shizhou Zhang, Donghao Chu, Di Xu

AAAI 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Masked autoencoder pretraining · 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
use entropy-based deterministic masking instead of random masking (ablation)DuGI-MAE · M3FD-inf detectionmAP: 57.2 -> 59.1Improved
use entropy-based masking instead of gray-value information-aware masking (ablation)DuGI-MAE · M3FD-inf detectionmAP: 58.4 -> 59.1Improved
add DDG module to MAE (ablation)MAE · M3FD-inf detectionmAP: 52.2 -> 53.1Improved
add DDG module to MCMAE (ablation)MCMAE · M3FD-inf detectionmAP: 56.8 -> 57.2Improved
add DDG module to InfMAE (ablation)InfMAE · M3FD-inf detectionmAP: 57.1 -> 57.6Improved
pretrain on Inf-590K instead of Inf30 (ablation)DuGI-MAE · M3FD-inf detectionmAP: 57.4 -> 59.1Improved
pretrain on Inf-590K instead of Inf30 (ablation)InfMAE · M3FD-inf detectionAP50: 88.2 -> 87.9Hurt
DuGI-MAE vs InfMAE on small target detectionDuGI-MAE · IRSTD-1kPd: 96.9 -> 95.9Hurt
DuGI-MAE vs InfMAE on semantic segmentation (FCN)DuGI-MAE · MSRSmIoU: 72.6 -> 73.1Improved

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