Adaptive Spatial Augmentation for Semi-supervised Semantic Segmentation
This work addresses the challenge of improving model generalization in semi-supervised semantic segmentation for computer vision applications, representing an incremental advancement by integrating spatial augmentations into existing frameworks.
The paper tackled the problem of enhancing semi-supervised semantic segmentation by proposing an adaptive spatial augmentation strategy that dynamically adjusts augmentations based on entropy, achieving state-of-the-art results on benchmark datasets like PASCAL VOC 2012, Cityscapes, and COCO.
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.