English(EN) CAPTOR: text-encoder-free grounding by counting caption co-occurrence over the visual words of a frozen encoder

新的CAPTOR方法可在没有文本编码器的情况下实现基于文本的图像引导

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-05 05:00

研究人员开发了一种名为CAPTOR的新颖方法，该方法无需配对的文本编码器即可实现基于文本的图像引导。该方法将图像编码器的patch token聚类为“视觉词”，并分析字幕共现来估计术语-patch矩阵。与现有的无训练基线相比，CAPTOR在COCO、Pascal VOC和Cityscapes等基准测试中表现出卓越的性能，甚至可以与经过文本对齐训练的模型相媲美。该方法在专业领域也显示出潜力，在乳腺癌幻灯片分析上表现优于强大的基线。 AI

影响该方法可以为未经过语言训练的模型实现基于文本的图像分析，从而拓宽在专业领域的应用。

排序理由该集群包含一篇详细介绍计算机视觉新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 26 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍计算机视觉新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Elad Yoshai, Natan T. Shaked · 2026-11-05 05:00

CAPTOR：通过计算冻结编码器的视觉词汇上的字幕共现来实现无文本编码器的基础

arXiv:2611.05599v1 Announce Type: new Abstract: Grounding a text query in an image needs a matrix scoring every term against every patch. Vision-language models compute it with an aligned text encoder, which many image encoders, such as histopathology-related models trained on sl…

本文如何被排名

报道来源 [1]

CAPTOR：通过计算冻结编码器的视觉词汇上的字幕共现来实现无文本编码器的基础

相关实体

相关话题