# Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement

arXiv: https://arxiv.org/abs/2201.01929 · HTML: https://mlsanity.com/paper/2201.01929/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 72 references that are in the map.
- First posted on arXiv 6 Jan 2022.

## Builds on (most cited first, 30 of 52)

- [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)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [Bidirectional Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/1904.10620/) (2019)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [DRIT++: Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1905.01270/) (2019)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?](https://mlsanity.com/paper/1610.01983/) (2016)
- [FSDR: Frequency Space Domain Randomization for Domain Generalization](https://mlsanity.com/paper/2103.02370/) (2021)
- [Unbiased Mean Teacher for Cross-domain Object Detection](https://mlsanity.com/paper/2003.00707/) (2020)
- [Exploring Object Relation in Mean Teacher for Cross-Domain Detection](https://mlsanity.com/paper/1904.11245/) (2019)
- [Exploring Categorical Regularization for Domain Adaptive Object Detection](https://mlsanity.com/paper/2003.09152/) (2020)
- [Learning to Balance Specificity and Invariance for In and Out of Domain Generalization](https://mlsanity.com/paper/2008.12839/) (2020)
- [Harmonizing Transferability and Discriminability for Adapting Object Detectors](https://mlsanity.com/paper/2003.06297/) (2020)
- [Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection](https://mlsanity.com/paper/1905.05396/) (2019)

## Built on by (most cited first, 15 of 15)

- [DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection](https://mlsanity.com/paper/2410.09004/) (2024)
- [Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillation](https://mlsanity.com/paper/2307.14709/) (2023)
- [S4DL: Shift-sensitive Spatial-Spectral Disentangling Learning for Hyperspectral Image Unsupervised Domain Adaptation](https://mlsanity.com/paper/2408.15263/) (2024)
- [Gated Domain-Invariant Feature Disentanglement for Domain Generalizable Object Detection](https://mlsanity.com/paper/2203.11432/) (2022)
- [Diffusion Domain Teacher: Diffusion Guided Domain Adaptive Object Detector](https://mlsanity.com/paper/2506.04211/) (2025)
- [Multi-source-free Domain Adaptation via Uncertainty-aware Adaptive Distillation](https://mlsanity.com/paper/2402.06213/) (2024)
- [Domain Expansion and Boundary Growth for Open-Set Single-Source Domain Generalization](https://mlsanity.com/paper/2411.02920/) (2024)
- [DAFD: Domain Adaptation via Feature Disentanglement for Image Classification](https://mlsanity.com/paper/2301.13337/) (2023)
- [SynthMix: Mixing up Aligned Synthesis for Medical Cross-Modality Domain Adaptation](https://mlsanity.com/paper/2305.04156/) (2023)
- [Cross Domain Object Detection via Multi-Granularity Confidence Alignment based Mean Teacher](https://mlsanity.com/paper/2407.07780/) (2024)
- [FIT: Frequency-based Image Translation for Domain Adaptive Object Detection](https://mlsanity.com/paper/2303.03698/) (2023)
- [Unsupervised Domain Adaptation for Neuron Membrane Segmentation based on Structural Features](https://mlsanity.com/paper/2305.02569/) (2023)
- [Learning Speaker-Invariant Visual Features for Lipreading](https://mlsanity.com/paper/2506.07572/) (2025)
- [Towards Conditional Feature Alignment for Cross-Domain Counting](https://mlsanity.com/paper/2506.17137/) (2025)
- [Vision-Reasoning-Guided Occlusion Removal from Light Fields](https://mlsanity.com/paper/2606.19985/) (2026)

## Abstract (arXiv)

Recent advances in unsupervised domain adaptation (UDA) techniques have witnessed great success in cross-domain computer vision tasks, enhancing the generalization ability of data-driven deep learning architectures by bridging the domain distribution gaps. For the UDA-based cross-domain object detection methods, the majority of them alleviate the domain bias by inducing the domain-invariant feature generation via adversarial learning strategy. However, their domain discriminators have limited classification ability due to the unstable adversarial training process. Therefore, the extracted features induced by them cannot be perfectly domain-invariant and still contain domain-private factors, bringing obstacles to further alleviate the cross-domain discrepancy. To tackle this issue, we design a Domain Disentanglement Faster-RCNN (DDF) to eliminate the source-specific information in the features for detection task learning. Our DDF method facilitates the feature disentanglement at the global and local stages, with a Global Triplet Disentanglement (GTD) module and an Instance Similarity Disentanglement (ISD) module, respectively. By outperforming state-of-the-art methods on four benchmark UDA object detection tasks, our DDF method is demonstrated to be effective with wide applicability.