Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation

TL;DR

This paper explores leveraging the Latent Diffusion Model for Few-shot Semantic Segmentation, introducing a novel framework called DiffewS that enhances interaction between query and support images, achieving superior results over existing methods.

Contribution

The paper proposes a new Diffusion-based framework, DiffewS, for Few-shot Semantic Segmentation, including a KV fusion method and support mask infusion, advancing the use of diffusion models in this domain.

Findings

DiffewS significantly outperforms previous SOTA models.

The KV fusion method improves interaction between query and support images.

Effective utilization of pre-training prior enhances segmentation performance.

Abstract

The Diffusion Model has not only garnered noteworthy achievements in the realm of image generation but has also demonstrated its potential as an effective pretraining method utilizing unlabeled data. Drawing from the extensive potential unveiled by the Diffusion Model in both semantic correspondence and open vocabulary segmentation, our work initiates an investigation into employing the Latent Diffusion Model for Few-shot Semantic Segmentation. Recently, inspired by the in-context learning ability of large language models, Few-shot Semantic Segmentation has evolved into In-context Segmentation tasks, morphing into a crucial element in assessing generalist segmentation models. In this context, we concentrate on Few-shot Semantic Segmentation, establishing a solid foundation for the future development of a Diffusion-based generalist model for segmentation. Our initial focus lies in understanding how to facilitate interaction between the query image and the support image, resulting in the proposal of a KV fusion method within the self-attention framework. Subsequently, we delve deeper into optimizing the infusion of information from the support mask and simultaneously re-evaluating how to provide reasonable supervision from the query mask. Based on our analysis, we establish a simple and effective framework named DiffewS, maximally retaining the original Latent Diffusion Model's generative framework and effectively utilizing the pre-training prior. Experimental results demonstrate that our method significantly outperforms the previous SOTA models in multiple settings.