Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2410.00900 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929522803212288 |
|---|---|
| author | Gerster, Robin Caesar, Holger Rapp, Matthias Wolpert, Alexander Teutsch, Michael |
| author_facet | Gerster, Robin Caesar, Holger Rapp, Matthias Wolpert, Alexander Teutsch, Michael |
| contents | Despite their success in various vision tasks, deep neural network architectures often underperform in out-of-distribution scenarios due to the difference between training and target domain style. To address this limitation, we introduce One-Shot Style Adaptation (OSSA), a novel unsupervised domain adaptation method for object detection that utilizes a single, unlabeled target image to approximate the target domain style. Specifically, OSSA generates diverse target styles by perturbing the style statistics derived from a single target image and then applies these styles to a labeled source dataset at the feature level using Adaptive Instance Normalization (AdaIN). Extensive experiments show that OSSA establishes a new state-of-the-art among one-shot domain adaptation methods by a significant margin, and in some cases, even outperforms strong baselines that use thousands of unlabeled target images. By applying OSSA in various scenarios, including weather, simulated-to-real (sim2real), and visual-to-thermal adaptations, our study explores the overarching significance of the style gap in these contexts. OSSA's simplicity and efficiency allow easy integration into existing frameworks, providing a potentially viable solution for practical applications with limited data availability. Code is available at https://github.com/RobinGerster7/OSSA |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_00900 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OSSA: Unsupervised One-Shot Style Adaptation Gerster, Robin Caesar, Holger Rapp, Matthias Wolpert, Alexander Teutsch, Michael Computer Vision and Pattern Recognition Despite their success in various vision tasks, deep neural network architectures often underperform in out-of-distribution scenarios due to the difference between training and target domain style. To address this limitation, we introduce One-Shot Style Adaptation (OSSA), a novel unsupervised domain adaptation method for object detection that utilizes a single, unlabeled target image to approximate the target domain style. Specifically, OSSA generates diverse target styles by perturbing the style statistics derived from a single target image and then applies these styles to a labeled source dataset at the feature level using Adaptive Instance Normalization (AdaIN). Extensive experiments show that OSSA establishes a new state-of-the-art among one-shot domain adaptation methods by a significant margin, and in some cases, even outperforms strong baselines that use thousands of unlabeled target images. By applying OSSA in various scenarios, including weather, simulated-to-real (sim2real), and visual-to-thermal adaptations, our study explores the overarching significance of the style gap in these contexts. OSSA's simplicity and efficiency allow easy integration into existing frameworks, providing a potentially viable solution for practical applications with limited data availability. Code is available at https://github.com/RobinGerster7/OSSA |
| title | OSSA: Unsupervised One-Shot Style Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.00900 |