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

arXiv: https://arxiv.org/abs/2512.04511 · HTML: https://mlsanity.com/paper/2512.04511/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Builds on (most cited first, 24 of 24)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection](https://mlsanity.com/paper/2203.16220/) (2022)
- [LLVIP: A Visible-infrared Paired Dataset for Low-light Vision](https://mlsanity.com/paper/2108.10831/) (2021)
- [Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning](https://mlsanity.com/paper/2003.02437/) (2020)
- [ConvMAE: Masked Convolution Meets Masked Autoencoders](https://mlsanity.com/paper/2205.03892/) (2022)
- [Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline](https://mlsanity.com/paper/2204.04120/) (2022)
- [Reweighted Infrared Patch-Tensor Model With Both Non-Local and Local Priors for Single-Frame Small Target Detection](https://mlsanity.com/paper/1703.09157/) (2017)
- [Infrared Small Target Detection with Scale and Location Sensitivity](https://mlsanity.com/paper/2403.19366/) (2024)
- [MILAN: Masked Image Pretraining on Language Assisted Representation](https://mlsanity.com/paper/2208.06049/) (2022)
- [LSOTB-TIR:A Large-Scale High-Diversity Thermal Infrared Object Tracking Benchmark](https://mlsanity.com/paper/2008.00836/) (2020)
- [ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2104.02967/) (2021)
- [MS-DETR: Multispectral Pedestrian Detection Transformer with Loosely Coupled Fusion and Modality-Balanced Optimization](https://mlsanity.com/paper/2302.00290/) (2023)
- [InfMAE: A Foundation Model in the Infrared Modality](https://mlsanity.com/paper/2402.00407/) (2024)
- [TBC-Net: A real-time detector for infrared small target detection using semantic constraint](https://mlsanity.com/paper/2001.05852/) (2019)
- [Detection-Friendly Nonuniformity Correction: A Union Framework for Infrared UAVTarget Detection](https://mlsanity.com/paper/2504.04012/) (2025)

## Abstract (arXiv)

Infrared imaging plays a critical role in low-light and adverse weather conditions. However, due to the distinct characteristics of infrared images, existing foundation models such as Masked Autoencoder (MAE) trained on visible data perform suboptimal in infrared image interpretation tasks. To bridge this gap, an infrared foundation model known as InfMAE was developed and pre-trained on large-scale infrared datasets. Despite its effectiveness, InfMAE still faces several limitations, including the omission of informative tokens, insufficient modeling of global associations, and neglect of non-uniform noise. In this paper, we propose a Dual-domain Guided Infrared foundation model based on MAE (DuGI-MAE). First, we design a deterministic masking strategy based on token entropy, preserving only high-entropy tokens for reconstruction to enhance informativeness. Next, we introduce a Dual-Domain Guidance (DDG) module, which simultaneously captures global token relationships and adaptively filters non-uniform background noise commonly present in infrared imagery. To facilitate large-scale pretraining, we construct Inf-590K, a comprehensive infrared image dataset encompassing diverse scenes, various target types, and multiple spatial resolutions. Pretrained on Inf-590K, DuGI-MAE demonstrates strong generalization capabilities across various downstream tasks, including infrared object detection, semantic segmentation, and small target detection. Experimental results validate the superiority of the proposed method over both supervised and self-supervised comparison methods. Our code is available in the supplementary material.