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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use entropy-based deterministic masking instead of random masking (ablation) | DuGI-MAE · M3FD-inf detection | mAP: 57.2 -> 59.1 | Improved |
| use entropy-based masking instead of gray-value information-aware masking (ablation) | DuGI-MAE · M3FD-inf detection | mAP: 58.4 -> 59.1 | Improved |
| add DDG module to MAE (ablation) | MAE · M3FD-inf detection | mAP: 52.2 -> 53.1 | Improved |
| add DDG module to MCMAE (ablation) | MCMAE · M3FD-inf detection | mAP: 56.8 -> 57.2 | Improved |
| add DDG module to InfMAE (ablation) | InfMAE · M3FD-inf detection | mAP: 57.1 -> 57.6 | Improved |
| pretrain on Inf-590K instead of Inf30 (ablation) | DuGI-MAE · M3FD-inf detection | mAP: 57.4 -> 59.1 | Improved |
| pretrain on Inf-590K instead of Inf30 (ablation) | InfMAE · M3FD-inf detection | AP50: 88.2 -> 87.9 | Hurt |
| DuGI-MAE vs InfMAE on small target detection | DuGI-MAE · IRSTD-1k | Pd: 96.9 -> 95.9 | Hurt |
| DuGI-MAE vs InfMAE on semantic segmentation (FCN) | DuGI-MAE · MSRS | mIoU: 72.6 -> 73.1 | 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.
- InfMAE — InfMAE: A Foundation Model in The Infrared Modality (ECCV 2024) · better on 8 of 9 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
- InfMAE: A Foundation Model in The Infrared Modality (ECCV 2024 · similarity 0.89)
- Denoising-Enhanced Coarse-to-Fine Infrared Small Target Detection with Attention Prior-Guided Knowledge Distillation (ECCV 2026 · similarity 0.86)
- Cross-domain Joint Learning with Prototype-guided Mixture-of-Experts for Infrared Moving Small Target Detection (AAAI 2026 · similarity 0.86)
- Rethinking Infrared Small Target Detection: A Foundation Driven Efficient Paradigm (NeurIPS 2026 · similarity 0.84)
- Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark (NeurIPS 2025 · similarity 0.84)
- Semi-supervised Infrared Small Target Detection with Thermodynamic-Inspired Uneven Perturbation and Confidence Adaptation (AAAI 2025 · similarity 0.83)
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.
