Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation

TL;DR

This paper introduces IACD, a novel image augmentation method using controlled diffusion to improve weakly-supervised semantic segmentation, especially with limited data, by generating diverse, high-quality images and selecting the best ones.

Contribution

The paper proposes a new augmentation framework with controlled diffusion and a high-quality image selection strategy for weakly-supervised semantic segmentation.

Findings

IACD outperforms existing methods, especially with small datasets.

Controlled diffusion effectively generates diverse images.

High-quality image selection reduces noise and improves results.

Abstract

Weakly-supervised semantic segmentation (WSSS), which aims to train segmentation models solely using image-level labels, has achieved significant attention. Existing methods primarily focus on generating high-quality pseudo labels using available images and their image-level labels. However, the quality of pseudo labels degrades significantly when the size of available dataset is limited. Thus, in this paper, we tackle this problem from a different view by introducing a novel approach called Image Augmentation with Controlled Diffusion (IACD). This framework effectively augments existing labeled datasets by generating diverse images through controlled diffusion, where the available images and image-level labels are served as the controlling information. Moreover, we also propose a high-quality image selection strategy to mitigate the potential noise introduced by the randomness of diffusion models. In the experiments, our proposed IACD approach clearly surpasses existing state-of-the-art methods. This effect is more obvious when the amount of available data is small, demonstrating the effectiveness of our method.