High-Performance Few-Shot Segmentation with Foundation Models: An Empirical Study

TL;DR

A simple approach to extract implicit knowledge from foundation models to construct coarse correspondence and introduce a lightweight decoder to refine coarse correspondence for fine-grained segmentation is proposed.

Abstract

Existing few-shot segmentation (FSS) methods mainly focus on designing novel support-query matching and self-matching mechanisms to exploit implicit knowledge in pre-trained backbones. However, the performance of these methods is often constrained by models pre-trained on classification tasks. The exploration of what types of pre-trained models can provide more beneficial implicit knowledge for FSS remains limited. In this paper, inspired by the representation consistency of foundational computer vision models, we develop a FSS framework based on foundation models. To be specific, we propose a simple approach to extract implicit knowledge from foundation models to construct coarse correspondence and introduce a lightweight decoder to refine coarse correspondence for fine-grained segmentation. We systematically summarize the performance of various foundation models on FSS and discover that the implicit knowledge within some of these models is more beneficial for FSS than models pre-trained on classification tasks. Extensive experiments on two widely used datasets demonstrate the effectiveness of our approach in leveraging the implicit knowledge of foundation models. Notably, the combination of DINOv2 and DFN exceeds previous state-of-the-art methods by 17.5% on COCO-20i. Code is available at https://github.com/DUT-CSJ/FoundationFSS.

Figures (2)

• Figure 1: Left: visualization of the vision knowledge of 7 foundation models and ViT pre-trained on the classification task. Right: visualization of the vision-language knowledge of 4 foundation models. Due to space constraints, only one example is shown for each foundation model.
• Figure 2: The architecture of our proposed framework.