# Few-shot Adaptive Object Detection with Cross-Domain CutMix

arXiv: https://arxiv.org/abs/2208.14586 · HTML: https://mlsanity.com/paper/2208.14586/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 51 references that are in the map.
- First posted on arXiv 31 Aug 2022.

## Builds on (most cited first, 30 of 31)

- [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)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [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)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [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)
- [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)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Deep Learning for Generic Object Detection: A Survey](https://mlsanity.com/paper/1809.02165/) (2018)
- [Textual Explanations for Self-Driving Vehicles](https://mlsanity.com/paper/1807.11546/) (2018)
- [Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?](https://mlsanity.com/paper/1610.01983/) (2016)
- [Progressive Domain Adaptation for Object Detection](https://mlsanity.com/paper/1910.11319/) (2019)
- [Efficient DETR: Improving End-to-End Object Detector with Dense Prior](https://mlsanity.com/paper/2104.01318/) (2021)
- [Multispectral Deep Neural Networks for Pedestrian Detection](https://mlsanity.com/paper/1611.02644/) (2016)
- [Between-class Learning for Image Classification](https://mlsanity.com/paper/1711.10284/) (2017)
- [Recent Advances in Deep Learning for Object Detection](https://mlsanity.com/paper/1908.03673/) (2019)
- [How Far are We from Solving Pedestrian Detection?](https://mlsanity.com/paper/1602.01237/) (2016)
- [Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning](https://mlsanity.com/paper/2110.03143/) (2021)
- [Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach](https://mlsanity.com/paper/1908.03856/) (2019)
- [DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations](https://mlsanity.com/paper/2011.11953/) (2020)
- [CutDepth:Edge-aware Data Augmentation in Depth Estimation](https://mlsanity.com/paper/2107.07684/) (2021)
- [Self-training Guided Adversarial Domain Adaptation For Thermal Imagery](https://mlsanity.com/paper/2106.07165/) (2021)

## Built on by (most cited first, 7 of 7)

- [D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection](https://mlsanity.com/paper/2403.09359/) (2024)
- [DODA: Adapting Object Detectors to Dynamic Agricultural Environments in Real-Time with Diffusion](https://mlsanity.com/paper/2403.18334/) (2024)
- [A Survey of Deep Visual Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2303.09253/) (2023)
- [Few-Shot Learning in Video and 3D Object Detection: A Survey](https://mlsanity.com/paper/2507.17079/) (2025)
- [SS-DC: Spatial-Spectral Decoupling and Coupling Across Visible-Infrared Gap for Domain Adaptive Object Detection](https://mlsanity.com/paper/2507.12017/) (2025)
- [Fusion for Visual-Infrared Person ReID in Real-World Surveillance Using Corrupted Multimodal Data](https://mlsanity.com/paper/2305.00320/) (2023)
- [From Dataset to Real-world: General 3D Object Detection via Generalized Cross-domain Few-shot Learning](https://mlsanity.com/paper/2503.06282/) (2025)

## Abstract (arXiv)

In object detection, data amount and cost are a trade-off, and collecting a large amount of data in a specific domain is labor intensive. Therefore, existing large-scale datasets are used for pre-training. However, conventional transfer learning and domain adaptation cannot bridge the domain gap when the target domain differs significantly from the source domain. We propose a data synthesis method that can solve the large domain gap problem. In this method, a part of the target image is pasted onto the source image, and the position of the pasted region is aligned by utilizing the information of the object bounding box. In addition, we introduce adversarial learning to discriminate whether the original or the pasted regions. The proposed method trains on a large number of source images and a few target domain images. The proposed method achieves higher accuracy than conventional methods in a very different domain problem setting, where RGB images are the source domain, and thermal infrared images are the target domain. Similarly, the proposed method achieves higher accuracy in the cases of simulation images to real images.