# EOVSAM: Efficient Open-Vocabulary Segmentation with SAM 3 in One Pass

Source: [EOVSAM: Efficient Open-Vocabulary Segmentation with SAM 3 in One Pass](<https://www.sota2.com/research/paper/6a7172b9bc6f0f07058462e4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-08-05T05:00:18.081Z

Authors: Haomin Peng, Yongkang Li, Zhaoxiang Liu, Xiaojie Jin, Shiguo Lian, Yunchao Wei, Xinggang Wang

Published: 2026-08-03T14:15:37.000Z

## Abstract

Open-vocabulary segmentation identifies and segments objects from arbitrary textual descriptions. SAM 3 supports noun-phrase-guided segmentation and achieves competitive open-vocabulary performance through exhaustive vocabulary traversal, yet suffers from prohibitive computational overhead as target categories scale. In this paper, we propose an Efficient Open-Vocabulary segmentation framework with SAM 3 (EOVSAM), which adapts SAM 3 for single-pass prediction. EOVSAM removes prompt conditioning to turn SAM 3 into an efficient mask generator and introduces a new Attentional Aggregation strategy to optimize open-vocabulary classification end-to-end. This formulation avoids the multi-stage pipelines and post-processing heuristics commonly used by existing methods, while mitigating the closed-set collapse that can arise when classification is optimized directly. EOVSAM consistently improves segmentation accuracy over vanilla SAM 3 on all evaluated datasets and accelerates inference by up to 338$\\times$. Furthermore, EOVSAM maintains high accuracy at lower resolutions while achieving even more remarkable inference speeds. Experiments on standard semantic and panoptic segmentation benchmarks show that EOVSAM combines competitive or state-of-the-art accuracy with a substantial speed advantage over existing open-vocabulary segmentation models. Code and models are available at https://github.com/hustvl/EOVSAM.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2608.02284>)

[PDF](<https://arxiv.org/pdf/2608.02284.pdf>)
