Cross-Domain Object Detection Using Unsupervised Image Translation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914260635877376 |
|---|---|
| author | Arruda, Vinicius F. Berriel, Rodrigo F. Paixão, Thiago M. Badue, Claudine De Souza, Alberto F. Sebe, Nicu Oliveira-Santos, Thiago |
| author_facet | Arruda, Vinicius F. Berriel, Rodrigo F. Paixão, Thiago M. Badue, Claudine De Souza, Alberto F. Sebe, Nicu Oliveira-Santos, Thiago |
| contents | Unsupervised domain adaptation for object detection addresses the adaption of detectors trained in a source domain to work accurately in an unseen target domain. Recently, methods approaching the alignment of the intermediate features proven to be promising, achieving state-of-the-art results. However, these methods are laborious to implement and hard to interpret. Although promising, there is still room for improvements to close the performance gap toward the upper-bound (when training with the target data). In this work, we propose a method to generate an artificial dataset in the target domain to train an object detector. We employed two unsupervised image translators (CycleGAN and an AdaIN-based model) using only annotated data from the source domain and non-annotated data from the target domain. Our key contributions are the proposal of a less complex yet more effective method that also has an improved interpretability. Results on real-world scenarios for autonomous driving show significant improvements, outperforming state-of-the-art methods in most cases, further closing the gap toward the upper-bound. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11779 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Cross-Domain Object Detection Using Unsupervised Image Translation Arruda, Vinicius F. Berriel, Rodrigo F. Paixão, Thiago M. Badue, Claudine De Souza, Alberto F. Sebe, Nicu Oliveira-Santos, Thiago Computer Vision and Pattern Recognition Unsupervised domain adaptation for object detection addresses the adaption of detectors trained in a source domain to work accurately in an unseen target domain. Recently, methods approaching the alignment of the intermediate features proven to be promising, achieving state-of-the-art results. However, these methods are laborious to implement and hard to interpret. Although promising, there is still room for improvements to close the performance gap toward the upper-bound (when training with the target data). In this work, we propose a method to generate an artificial dataset in the target domain to train an object detector. We employed two unsupervised image translators (CycleGAN and an AdaIN-based model) using only annotated data from the source domain and non-annotated data from the target domain. Our key contributions are the proposal of a less complex yet more effective method that also has an improved interpretability. Results on real-world scenarios for autonomous driving show significant improvements, outperforming state-of-the-art methods in most cases, further closing the gap toward the upper-bound. |
| title | Cross-Domain Object Detection Using Unsupervised Image Translation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.11779 |