# Detect, Augment, Compose, and Adapt: Four Steps for Unsupervised Domain Adaptation in Object Detection

arXiv: https://arxiv.org/abs/2308.15353 · HTML: https://mlsanity.com/paper/2308.15353/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 61 references that are in the map.
- First posted on arXiv 29 Aug 2023.

## Builds on (most cited first, 30 of 44)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Measuring Catastrophic Forgetting in Neural Networks](https://mlsanity.com/paper/1708.02072/) (2017)
- [Few-shot Object Detection via Feature Reweighting](https://mlsanity.com/paper/1812.01866/) (2018)
- [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)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1607.03516/) (2016)
- [A review of domain adaptation without target labels](https://mlsanity.com/paper/1901.05335/) (2019)
- [Learning Data Augmentation Strategies for Object Detection](https://mlsanity.com/paper/1906.11172/) (2019)
- [Cross-Domain Adaptive Teacher for Object Detection](https://mlsanity.com/paper/2111.13216/) (2021)
- [Few-Shot Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.02536/) (2017)
- [Cross-domain Detection via Graph-induced Prototype Alignment](https://mlsanity.com/paper/2003.12849/) (2020)
- [Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector](https://mlsanity.com/paper/2008.08574/) (2020)
- [MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection](https://mlsanity.com/paper/2103.04224/) (2021)
- [Dual Mixup Regularized Learning for Adversarial Domain Adaptation](https://mlsanity.com/paper/2007.03141/) (2020)
- [DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation](https://mlsanity.com/paper/2104.10834/) (2021)
- [A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data](https://mlsanity.com/paper/2012.05400/) (2020)
- [SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.06398/) (2022)
- [Spatial Attention Pyramid Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2003.12979/) (2020)
- [Adapting Object Detectors with Conditional Domain Normalization](https://mlsanity.com/paper/2003.07071/) (2020)
- [Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.15793/) (2022)

## Built on by (most cited first, 4 of 4)

- [A Large-scale Multi Domain Leukemia Dataset for the White Blood Cells Detection with Morphological Attributes for Explainability](https://mlsanity.com/paper/2405.10803/) (2024)
- [Wild Berry image dataset collected in Finnish forests and peatlands using drones](https://mlsanity.com/paper/2405.07550/) (2024)
- [Leveraging Sparse Annotations for Leukemia Diagnosis on the Large Leukemia Dataset](https://mlsanity.com/paper/2504.02602/) (2025)
- [Leveraging Confident Image Regions for Source-Free Domain-Adaptive Object Detection](https://mlsanity.com/paper/2501.10081/) (2025)

## Abstract (arXiv)

Unsupervised domain adaptation (UDA) plays a crucial role in object detection when adapting a source-trained detector to a target domain without annotated data. In this paper, we propose a novel and effective four-step UDA approach that leverages self-supervision and trains source and target data concurrently. We harness self-supervised learning to mitigate the lack of ground truth in the target domain. Our method consists of the following steps: (1) identify the region with the highest-confidence set of detections in each target image, which serve as our pseudo-labels; (2) crop the identified region and generate a collection of its augmented versions; (3) combine these latter into a composite image; (4) adapt the network to the target domain using the composed image. Through extensive experiments under cross-camera, cross-weather, and synthetic-to-real scenarios, our approach achieves state-of-the-art performance, improving upon the nearest competitor by more than 2% in terms of mean Average Precision (mAP). The code is available at https://github.com/MohamedTEV/DACA.