ProSAM: Enhancing the Robustness of SAM-based Visual Reference Segmentation with Probabilistic Prompts

TL;DR

ProSAM introduces a probabilistic prompt encoder for SAM-based visual segmentation, significantly improving robustness and stability by avoiding boundary prompts, and outperforms existing methods on standard datasets.

Contribution

It proposes a variational prompt encoder that predicts prompt distributions, enhancing robustness in SAM-based visual reference segmentation.

Findings

Outperforms state-of-the-art on Pascal-5i and COCO-20i datasets

Achieves more stable and robust segmentation results

Addresses prompt boundary instability in existing methods

Abstract

The recent advancements in large foundation models have driven the success of open-set image segmentation, a task focused on segmenting objects beyond predefined categories. Among various prompt types (such as points, boxes, texts, and visual references), visual reference segmentation stands out for its unique flexibility and strong zero-shot capabilities. Recently, several SAM-based methods have made notable progress in this task by automatically generating prompts to guide SAM. However, these methods often generate prompts at boundaries of target regions due to suboptimal prompt encoder, which results in instability and reduced robustness. In this work, we introduce ProSAM, a simple but effective method to address the stability challenges we identified in existing SAM-based visual reference segmentation approaches. By learning a variational prompt encoder to predict multivariate prompt distributions, ProSAM avoids generating prompts that lie in unstable regions, overcoming the instability caused by less robust prompts. Our approach consistently surpasses state-of-the-art methods on the Pascal-5$^i$ and COCO-20$^i$ datasets, providing a more robust solution for visual reference segmentation.