CVAIMay 17, 2025

AoP-SAM: Automation of Prompts for Efficient Segmentation

arXiv:2505.11980v15 citationsh-index: 2AAAI
Originality Incremental advance
AI Analysis

This work addresses the need for automated segmentation in scenarios requiring rapid and resource-efficient processing, though it is incremental as it builds on SAM's existing capabilities.

The paper tackled the problem of manual prompt engineering being impractical for real-world applications of the Segment Anything Model (SAM) by proposing AoP-SAM, which automatically generates prompts in optimal locations, resulting in improved efficiency and accuracy on three datasets.

The Segment Anything Model (SAM) is a powerful foundation model for image segmentation, showing robust zero-shot generalization through prompt engineering. However, relying on manual prompts is impractical for real-world applications, particularly in scenarios where rapid prompt provision and resource efficiency are crucial. In this paper, we propose the Automation of Prompts for SAM (AoP-SAM), a novel approach that learns to generate essential prompts in optimal locations automatically. AoP-SAM enhances SAM's efficiency and usability by eliminating manual input, making it better suited for real-world tasks. Our approach employs a lightweight yet efficient Prompt Predictor model that detects key entities across images and identifies the optimal regions for placing prompt candidates. This method leverages SAM's image embeddings, preserving its zero-shot generalization capabilities without requiring fine-tuning. Additionally, we introduce a test-time instance-level Adaptive Sampling and Filtering mechanism that generates prompts in a coarse-to-fine manner. This notably enhances both prompt and mask generation efficiency by reducing computational overhead and minimizing redundant mask refinements. Evaluations of three datasets demonstrate that AoP-SAM substantially improves both prompt generation efficiency and mask generation accuracy, making SAM more effective for automated segmentation tasks.

Foundations

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

Your Notes