English(EN) What Remains OOD? OODConceptBench for Open-World Concept Recognition in Vision-Language Models

新基准揭示视觉语言模型在开放世界概念方面存在困难

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

研究人员开发了OODConceptBench，这是一个旨在评估视觉语言模型在开放世界场景中识别概念能力的新基准。该基准包含完整数据集（L1）中的30,752张图像和更难的子集（L2）中的14,285张图像，涵盖了七个类别中的560个概念短语。对37个模型的评估显示，L2上的性能始终低于L1，并且较新模型在开放世界概念识别方面并不总是优于旧模型，这表明分布外挑战依然存在。 AI

影响强调了视觉语言模型在开放世界概念识别方面持续存在的挑战，为未来的研究和开发指明了方向。

排序理由该集群描述了一篇介绍用于评估AI模型基准的新学术论文。[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: 9 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇介绍用于评估AI模型基准的新学术论文。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Zhiran Luo, Zhiyong Yang, Zitai Wang, Sicong Li, Qianqian Xu, Qingming Huang · 2026-10-27 04:00

OOD概念仍存？OODConceptBench用于视觉语言模型的开放世界概念识别

arXiv:2610.33564v1 Announce Type: new Abstract: In the era of large-scale pretrained models, zero-shot generalization has increasingly blurred the boundary between known and unknown concepts. However, current evaluations do not directly reveal which open-world concepts different …

本文如何被排名

报道来源 [1]

OOD概念仍存？OODConceptBench用于视觉语言模型的开放世界概念识别

相关实体

相关话题