SAM-SP: Self-Prompting Makes SAM Great Again

TL;DR

SAM-SP introduces a self-prompting fine-tuning method for the Segment Anything Model, enabling autonomous prompt generation and improved domain-specific segmentation without expert prompts, outperforming existing approaches.

Contribution

The paper proposes SAM-SP, a novel self-prompting and self-distillation approach that enhances SAM's domain adaptation and reduces reliance on expert prompts during evaluation.

Findings

SAM-SP outperforms state-of-the-art segmentation methods.

It significantly reduces dependence on expert prompts.

Demonstrates strong results across various domain-specific datasets.

Abstract

The recently introduced Segment Anything Model (SAM), a Visual Foundation Model (VFM), has demonstrated impressive capabilities in zero-shot segmentation tasks across diverse natural image datasets. Despite its success, SAM encounters noticeably performance degradation when applied to specific domains, such as medical images. Current efforts to address this issue have involved fine-tuning strategies, intended to bolster the generalizability of the vanilla SAM. However, these approaches still predominantly necessitate the utilization of domain specific expert-level prompts during the evaluation phase, which severely constrains the model's practicality. To overcome this limitation, we introduce a novel self-prompting based fine-tuning approach, called SAM-SP, tailored for extending the vanilla SAM model. Specifically, SAM-SP leverages the output from the previous iteration of the model itself as prompts to guide subsequent iteration of the model. This self-prompting module endeavors to learn how to generate useful prompts autonomously and alleviates the dependence on expert prompts during the evaluation phase, significantly broadening SAM's applicability. Additionally, we integrate a self-distillation module to enhance the self-prompting process further. Extensive experiments across various domain specific datasets validate the effectiveness of the proposed SAM-SP. Our SAM-SP not only alleviates the reliance on expert prompts but also exhibits superior segmentation performance comparing to the state-of-the-art task-specific segmentation approaches, the vanilla SAM, and SAM-based approaches.