Adaptive Spatial Augmentation for Semi-supervised Semantic Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912402379898880 |
|---|---|
| author | Ran, Lingyan Li, Yali Zhuo, Tao Zhang, Shizhou Zhang, Yanning |
| author_facet | Ran, Lingyan Li, Yali Zhuo, Tao Zhang, Shizhou Zhang, Yanning |
| contents | In semi-supervised semantic segmentation (SSSS), data augmentation plays a crucial role in the weak-to-strong consistency regularization framework, as it enhances diversity and improves model generalization. Recent strong augmentation methods have primarily focused on intensity-based perturbations, which have minimal impact on the semantic masks. In contrast, spatial augmentations like translation and rotation have long been acknowledged for their effectiveness in supervised semantic segmentation tasks, but they are often ignored in SSSS. In this work, we demonstrate that spatial augmentation can also contribute to model training in SSSS, despite generating inconsistent masks between the weak and strong augmentations. Furthermore, recognizing the variability among images, we propose an adaptive augmentation strategy that dynamically adjusts the augmentation for each instance based on entropy. Extensive experiments show that our proposed Adaptive Spatial Augmentation (\textbf{ASAug}) can be integrated as a pluggable module, consistently improving the performance of existing methods and achieving state-of-the-art results on benchmark datasets such as PASCAL VOC 2012, Cityscapes, and COCO. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23438 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adaptive Spatial Augmentation for Semi-supervised Semantic Segmentation Ran, Lingyan Li, Yali Zhuo, Tao Zhang, Shizhou Zhang, Yanning Computer Vision and Pattern Recognition In semi-supervised semantic segmentation (SSSS), data augmentation plays a crucial role in the weak-to-strong consistency regularization framework, as it enhances diversity and improves model generalization. Recent strong augmentation methods have primarily focused on intensity-based perturbations, which have minimal impact on the semantic masks. In contrast, spatial augmentations like translation and rotation have long been acknowledged for their effectiveness in supervised semantic segmentation tasks, but they are often ignored in SSSS. In this work, we demonstrate that spatial augmentation can also contribute to model training in SSSS, despite generating inconsistent masks between the weak and strong augmentations. Furthermore, recognizing the variability among images, we propose an adaptive augmentation strategy that dynamically adjusts the augmentation for each instance based on entropy. Extensive experiments show that our proposed Adaptive Spatial Augmentation (\textbf{ASAug}) can be integrated as a pluggable module, consistently improving the performance of existing methods and achieving state-of-the-art results on benchmark datasets such as PASCAL VOC 2012, Cityscapes, and COCO. |
| title | Adaptive Spatial Augmentation for Semi-supervised Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.23438 |