AoP-SAM: Automation of Prompts for Efficient Segmentation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Yi, Son, Mu-Young, Hua, Chuanbo, Kim, Joo-Young
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910950921076736
author Chen, Yi
Son, Mu-Young
Hua, Chuanbo
Kim, Joo-Young
author_facet Chen, Yi
Son, Mu-Young
Hua, Chuanbo
Kim, Joo-Young
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11980
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AoP-SAM: Automation of Prompts for Efficient Segmentation
Chen, Yi
Son, Mu-Young
Hua, Chuanbo
Kim, Joo-Young
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title AoP-SAM: Automation of Prompts for Efficient Segmentation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.11980