Divide, Ensemble and Conquer: The Last Mile on Unsupervised Domain Adaptation for Semantic Segmentation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910727706509312 |
|---|---|
| author | Lian, Tao Gómez, Jose L. López, Antonio M. |
| author_facet | Lian, Tao Gómez, Jose L. López, Antonio M. |
| contents | The last mile of unsupervised domain adaptation (UDA) for semantic segmentation is the challenge of solving the syn-to-real domain gap. Recent UDA methods have progressed significantly, yet they often rely on strategies customized for synthetic single-source datasets (e.g., GTA5), which limits their generalisation to multi-source datasets. Conversely, synthetic multi-source datasets hold promise for advancing the last mile of UDA but remain underutilized in current research. Thus, we propose DEC, a flexible UDA framework for multi-source datasets. Following a divide-and-conquer strategy, DEC simplifies the task by categorizing semantic classes, training models for each category, and fusing their outputs by an ensemble model trained exclusively on synthetic datasets to obtain the final segmentation mask. DEC can integrate with existing UDA methods, achieving state-of-the-art performance on Cityscapes, BDD100K, and Mapillary Vistas, significantly narrowing the syn-to-real domain gap. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_18809 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Divide, Ensemble and Conquer: The Last Mile on Unsupervised Domain Adaptation for Semantic Segmentation Lian, Tao Gómez, Jose L. López, Antonio M. Computer Vision and Pattern Recognition The last mile of unsupervised domain adaptation (UDA) for semantic segmentation is the challenge of solving the syn-to-real domain gap. Recent UDA methods have progressed significantly, yet they often rely on strategies customized for synthetic single-source datasets (e.g., GTA5), which limits their generalisation to multi-source datasets. Conversely, synthetic multi-source datasets hold promise for advancing the last mile of UDA but remain underutilized in current research. Thus, we propose DEC, a flexible UDA framework for multi-source datasets. Following a divide-and-conquer strategy, DEC simplifies the task by categorizing semantic classes, training models for each category, and fusing their outputs by an ensemble model trained exclusively on synthetic datasets to obtain the final segmentation mask. DEC can integrate with existing UDA methods, achieving state-of-the-art performance on Cityscapes, BDD100K, and Mapillary Vistas, significantly narrowing the syn-to-real domain gap. |
| title | Divide, Ensemble and Conquer: The Last Mile on Unsupervised Domain Adaptation for Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.18809 |