PulseAugur
实时 12:02:28
English(EN) ActiveSAM: Image-Conditional Class Pruning for Fast and Accurate Open-Vocabulary Segmentation

ActiveSAM框架提升分割速度和准确性

研究人员开发了ActiveSAM,一个新颖的框架,旨在利用Segment Anything Model 3 (SAM 3) 提高开放词汇语义分割的效率和准确性。这种无需训练、零样本的方法通过识别与每张图像相关的活动类别子集来优化分割过程,从而降低计算负载。ActiveSAM在速度和准确性方面均有显著提升,优于SegEarth-OV3等现有最先进方法,并对图像损坏表现出强大的鲁棒性,使其适用于现实世界应用。 AI

影响 ActiveSAM的效率提升有望加速开放词汇分割在自动驾驶等现实世界应用中的部署。

排序理由 该集群描述了一篇详细介绍新颖图像分割框架的研究论文。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Tran Dinh Tien, Zhiqiang Shen ·

    ActiveSAM: Image-Conditional Class Pruning for Fast and Accurate Open-Vocabulary Segmentation

    arXiv:2606.16996v1 Announce Type: cross Abstract: Segment Anything Model 3 (SAM 3) provides a strong frozen backbone for concept-prompted segmentation, but applying it directly to open-vocabulary semantic segmentation (OVSS) is inefficient: full-resolution decoding is typically r…

  2. arXiv cs.CV TIER_1 English(EN) · Zhiqiang Shen ·

    ActiveSAM: Image-Conditional Class Pruning for Fast and Accurate Open-Vocabulary Segmentation

    Segment Anything Model 3 (SAM 3) provides a strong frozen backbone for concept-prompted segmentation, but applying it directly to open-vocabulary semantic segmentation (OVSS) is inefficient: full-resolution decoding is typically run over the entire dataset vocabulary, whereas eac…