CVNov 27, 2023

Stable Segment Anything Model

arXiv:2311.15776v215 citationsh-index: 23Has Code
Originality Incremental advance
AI Analysis

This addresses the need for more user-friendly and stable segmentation tools in computer vision, though it is incremental as it builds directly on SAM.

The paper tackles the problem of making the Segment Anything Model (SAM) robust to low-quality prompts like imprecise bounding boxes and insufficient points, achieving improved segmentation stability across a wide range of prompt qualities with minimal learnable parameters (0.08 M) and fast adaptation (1 training epoch).

The Segment Anything Model (SAM) achieves remarkable promptable segmentation given high-quality prompts which, however, often require good skills to specify. To make SAM robust to casual prompts, this paper presents the first comprehensive analysis on SAM's segmentation stability across a diverse spectrum of prompt qualities, notably imprecise bounding boxes and insufficient points. Our key finding reveals that given such low-quality prompts, SAM's mask decoder tends to activate image features that are biased towards the background or confined to specific object parts. To mitigate this issue, our key idea consists of calibrating solely SAM's mask attention by adjusting the sampling locations and amplitudes of image features, while the original SAM model architecture and weights remain unchanged. Consequently, our deformable sampling plugin (DSP) enables SAM to adaptively shift attention to the prompted target regions in a data-driven manner, facilitated by our effective robust training strategy (RTS). During inference, dynamic routing plugin (DRP) is proposed that toggles SAM between the deformable and regular grid sampling modes, conditioned on the input prompt quality. Thus, our solution, termed Stable-SAM, offers several advantages: 1) improved SAM's segmentation stability across a wide range of prompt qualities, while 2) retaining SAM's powerful promptable segmentation efficiency and generality, with 3) minimal learnable parameters (0.08 M) and fast adaptation (by 1 training epoch). Extensive experiments across multiple datasets validate the effectiveness and advantages of our approach, underscoring Stable-SAM as a more robust solution for segmenting anything. Codes will be released upon acceptance. https://github.com/fanq15/Stable-SAM

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes