# Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning

arXiv: https://arxiv.org/abs/2110.03143 · HTML: https://mlsanity.com/paper/2110.03143/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 47 references that are in the map.
- First posted on arXiv 7 Oct 2021.

## Builds on (most cited first, 28 of 28)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Deep Learning for Generic Object Detection: A Survey](https://mlsanity.com/paper/1809.02165/) (2018)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Exploring Object Relation in Mean Teacher for Cross-Domain Detection](https://mlsanity.com/paper/1904.11245/) (2019)
- [Progressive Domain Adaptation for Object Detection](https://mlsanity.com/paper/1910.11319/) (2019)
- [Feature-Critic Networks for Heterogeneous Domain Generalization](https://mlsanity.com/paper/1901.11448/) (2019)
- [Harmonizing Transferability and Discriminability for Adapting Object Detectors](https://mlsanity.com/paper/2003.06297/) (2020)
- [A Robust Learning Approach to Domain Adaptive Object Detection](https://mlsanity.com/paper/1904.02361/) (2019)
- [MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection](https://mlsanity.com/paper/2103.04224/) (2021)
- [Unsupervised Domain Adaptation of Object Detectors: A Survey](https://mlsanity.com/paper/2105.13502/) (2021)
- [Evolved Policy Gradients](https://mlsanity.com/paper/1802.04821/) (2018)
- [Automatic adaptation of object detectors to new domains using self-training](https://mlsanity.com/paper/1904.07305/) (2019)
- [Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2004.04398/) (2020)
- [Borrow from Anywhere: Pseudo Multi-modal Object Detection in Thermal Imagery](https://mlsanity.com/paper/1905.08789/) (2019)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling](https://mlsanity.com/paper/1505.07293/) (2015)
- [SF-UDA3D: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detection](https://mlsanity.com/paper/2010.08243/) (2020)
- [SSTN: Self-Supervised Domain Adaptation Thermal Object Detection for Autonomous Driving](https://mlsanity.com/paper/2103.03150/) (2021)
- [Uncertainty-aware Mean Teacher for Source-free Unsupervised Domain Adaptive 3D Object Detection](https://mlsanity.com/paper/2109.14651/) (2021)

## Built on by (most cited first, 25 of 25)

- [CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition](https://mlsanity.com/paper/2303.11313/) (2023)
- [Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.15793/) (2022)
- [Towards Online Domain Adaptive Object Detection](https://mlsanity.com/paper/2204.05289/) (2022)
- [Caltech Aerial RGB-Thermal Dataset in the Wild](https://mlsanity.com/paper/2403.08997/) (2024)
- [Long-range UAV Thermal Geo-localization with Satellite Imagery](https://mlsanity.com/paper/2306.02994/) (2023)
- [Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation](https://mlsanity.com/paper/2303.14361/) (2023)
- [D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection](https://mlsanity.com/paper/2403.09359/) (2024)
- [Pedestrian Detection in Low-Light Conditions: A Comprehensive Survey](https://mlsanity.com/paper/2401.07801/) (2024)
- [Few-shot Adaptive Object Detection with Cross-Domain CutMix](https://mlsanity.com/paper/2208.14586/) (2022)
- [Few-Shot Learning of Compact Models via Task-Specific Meta Distillation](https://mlsanity.com/paper/2210.09922/) (2022)
- [Open-Set Automatic Target Recognition](https://mlsanity.com/paper/2211.05883/) (2022)
- [Zero-Shot Scene Understanding for Automatic Target Recognition Using Large Vision-Language Models](https://mlsanity.com/paper/2501.07396/) (2025)
- [DSERT-RoLL: Robust Multi-Modal Perception for Diverse Driving Conditions with Stereo Event-RGB-Thermal Cameras, 4D Radar, and Dual-LiDAR](https://mlsanity.com/paper/2604.03685/) (2026)
- [Deep Transductive Transfer Learning for Automatic Target Recognition](https://mlsanity.com/paper/2305.13886/) (2023)
- [ShadowSense: Unsupervised Domain Adaptation and Feature Fusion for Shadow-Agnostic Tree Crown Detection from RGB-Thermal Drone Imagery](https://mlsanity.com/paper/2310.16212/) (2023)
- [Contrastive Learning and Cycle Consistency-based Transductive Transfer Learning for Target Annotation](https://mlsanity.com/paper/2401.12340/) (2024)
- [Improving Online Source-free Domain Adaptation for Object Detection by Unsupervised Data Acquisition](https://mlsanity.com/paper/2310.19258/) (2023)
- [SS-DC: Spatial-Spectral Decoupling and Coupling Across Visible-Infrared Gap for Domain Adaptive Object Detection](https://mlsanity.com/paper/2507.12017/) (2025)
- [Exploring Syn-to-Real Domain Adaptation for Military Target Detection](https://mlsanity.com/paper/2512.23208/) (2025)
- [Rewarded meta-pruning: Meta Learning with Rewards for Channel Pruning](https://mlsanity.com/paper/2301.11063/) (2023)
- [Towards Reducing Data Acquisition and Labeling for Defect Detection using Simulated Data](https://mlsanity.com/paper/2406.19175/) (2024)
- [OSSA: Unsupervised One-Shot Style Adaptation](https://mlsanity.com/paper/2410.00900/) (2024)
- [Hyperspectral Image Cross-Domain Object Detection Method based on Spectral-Spatial Feature Alignment](https://mlsanity.com/paper/2411.16772/) (2024)
- [FDCT: Frequency-Aware Decomposition and Cross-Modal Token-Alignment for Multi-Sensor Target Classification](https://mlsanity.com/paper/2503.09873/) (2025)
- [Thermal-Det: Language-Guided Cross-Modal Distillation for Open-Vocabulary Thermal Object Detection](https://mlsanity.com/paper/2605.10130/) (2026)

## Abstract (arXiv)

Object detectors trained on large-scale RGB datasets are being extensively employed in real-world applications. However, these RGB-trained models suffer a performance drop under adverse illumination and lighting conditions. Infrared (IR) cameras are robust under such conditions and can be helpful in real-world applications. Though thermal cameras are widely used for military applications and increasingly for commercial applications, there is a lack of robust algorithms to robustly exploit the thermal imagery due to the limited availability of labeled thermal data. In this work, we aim to enhance the object detection performance in the thermal domain by leveraging the labeled visible domain data in an Unsupervised Domain Adaptation (UDA) setting. We propose an algorithm agnostic meta-learning framework to improve existing UDA methods instead of proposing a new UDA strategy. We achieve this by meta-learning the initial condition of the detector, which facilitates the adaptation process with fine updates without overfitting or getting stuck at local optima. However, meta-learning the initial condition for the detection scenario is computationally heavy due to long and intractable computation graphs. Therefore, we propose an online meta-learning paradigm which performs online updates resulting in a short and tractable computation graph. To this end, we demonstrate the superiority of our method over many baselines in the UDA setting, producing a state-of-the-art thermal detector for the KAIST and DSIAC datasets.