# Spectral Transfer Guided Active Domain Adaptation For Thermal Imagery

arXiv: https://arxiv.org/abs/2304.07031 · HTML: https://mlsanity.com/paper/2304.07031/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 49 references that are in the map.
- First posted on arXiv 14 Apr 2023.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (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)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [Contextual Diversity for Active Learning](https://mlsanity.com/paper/2008.05723/) (2020)
- [Multispectral Deep Neural Networks for Pedestrian Detection](https://mlsanity.com/paper/1611.02644/) (2016)
- [Active Adversarial Domain Adaptation](https://mlsanity.com/paper/1904.07848/) (2019)
- [Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings](https://mlsanity.com/paper/2010.08666/) (2020)
- [Active Learning for Deep Detection Neural Networks](https://mlsanity.com/paper/1911.09168/) (2019)
- [Active Learning for Domain Adaptation: An Energy-Based Approach](https://mlsanity.com/paper/2112.01406/) (2021)
- [Borrow from Anywhere: Pseudo Multi-modal Object Detection in Thermal Imagery](https://mlsanity.com/paper/1905.08789/) (2019)
- [S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation](https://mlsanity.com/paper/2109.08901/) (2021)
- [MCDAL: Maximum Classifier Discrepancy for Active Learning](https://mlsanity.com/paper/2107.11049/) (2021)
- [Learning Distinctive Margin toward Active Domain Adaptation](https://mlsanity.com/paper/2203.05738/) (2022)
- [Unsupervised Domain Adaptation using Regularized Hyper-graph Matching](https://mlsanity.com/paper/1805.08874/) (2018)
- [Self-training Guided Adversarial Domain Adaptation For Thermal Imagery](https://mlsanity.com/paper/2106.07165/) (2021)
- [Unsupervised Domain Adaptation for Multispectral Pedestrian Detection](https://mlsanity.com/paper/1904.03692/) (2019)
- [Augmentation of Atmospheric Turbulence Effects on Thermal Adapted Object Detection Models](https://mlsanity.com/paper/2204.08745/) (2022)
- [Transfering Low-Frequency Features for Domain Adaptation](https://mlsanity.com/paper/2208.14706/) (2022)

## Built on by (most cited first, 3 of 3)

- [Caltech Aerial RGB-Thermal Dataset in the Wild](https://mlsanity.com/paper/2403.08997/) (2024)
- [SAGA: Semantic-Aware Gray color Augmentation for Visible-to-Thermal Domain Adaptation across Multi-View Drone and Ground-Based Vision Systems](https://mlsanity.com/paper/2504.15728/) (2025)
- [Leveraging Confident Image Regions for Source-Free Domain-Adaptive Object Detection](https://mlsanity.com/paper/2501.10081/) (2025)

## Abstract (arXiv)

The exploitation of visible spectrum datasets has led deep networks to show remarkable success. However, real-world tasks include low-lighting conditions which arise performance bottlenecks for models trained on large-scale RGB image datasets. Thermal IR cameras are more robust against such conditions. Therefore, the usage of thermal imagery in real-world applications can be useful. Unsupervised domain adaptation (UDA) allows transferring information from a source domain to a fully unlabeled target domain. Despite substantial improvements in UDA, the performance gap between UDA and its supervised learning counterpart remains significant. By picking a small number of target samples to annotate and using them in training, active domain adaptation tries to mitigate this gap with minimum annotation expense. We propose an active domain adaptation method in order to examine the efficiency of combining the visible spectrum and thermal imagery modalities. When the domain gap is considerably large as in the visible-to-thermal task, we may conclude that the methods without explicit domain alignment cannot achieve their full potential. To this end, we propose a spectral transfer guided active domain adaptation method to select the most informative unlabeled target samples while aligning source and target domains. We used the large-scale visible spectrum dataset MS-COCO as the source domain and the thermal dataset FLIR ADAS as the target domain to present the results of our method. Extensive experimental evaluation demonstrates that our proposed method outperforms the state-of-the-art active domain adaptation methods. The code and models are publicly available.