Causal Prompt Calibration Guided Segment Anything Model for Open-Vocabulary Multi-Entity Segmentation

TL;DR

This paper introduces CPC-SAM, a causal prompt calibration method that improves open-vocabulary multi-entity segmentation by eliminating prompt confounders, leading to better generalization of the Segment Anything Model.

Contribution

It proposes a causal analysis framework and a novel calibration method, CPC-SAM, to enhance SAM's performance in open-vocabulary multi-entity segmentation.

Findings

CPC-SAM outperforms existing methods in OVMS tasks.

Causal prompt calibration reduces generalization errors.

Theoretical analysis supports the effectiveness of causal prompts.

Abstract

Despite the strength of the Segment Anything Model (SAM), it struggles with generalization issues in open-vocabulary multi-entity segmentation (OVMS). Through empirical and causal analyses, we find that (i) the prompt bias is the primary cause of the generalization issues; (ii) this bias is closely tied to the task-irrelevant generating factors within the prompts, which act as confounders and affect generalization. To address the generalization issues, we aim to propose a method that can calibrate prompts to eliminate confounders for accurate OVMS. Building upon the causal analysis, we propose that the optimal prompt for OVMS should contain only task-relevant causal factors. We define it as the causal prompt, serving as the goal of calibration. Next, our theoretical analysis, grounded by causal multi-distribution consistency theory, proves that this prompt can be obtained by enforcing segmentation consistency and optimality. Inspired by this, we propose CPC-SAM, a Causal Prompt Calibration method for SAM to achieve accurate OVMS. It integrates a lightweight causal prompt learner (CaPL) into SAM to obtain causal prompts. Specifically, we first generate multiple prompts using random annotations to simulate diverse distributions and then reweight them via CaPL by enforcing causal multi-distribution consistency in both task and entity levels. To ensure obtaining causal prompts, CaPL is optimized by minimizing the cumulative segmentation loss across the reweighted prompts to achieve consistency and optimality. A bi-level optimization strategy alternates between optimizing CaPL and SAM, ensuring accurate OVMS. Extensive experiments validate its superiority.