English(EN) VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Tokenization and Vector Database Retrieval

VocaDet框架无需重新训练即可实现开放词汇目标检测

作者 PulseAugur 编辑部 · [2 个来源] · 2026-07-09 14:35

研究人员推出了一种新颖的开放词汇目标检测和分割框架VocaDet。该系统无需模型重新训练，即可从用户提供的正负样本中学习目标概念。VocaDet将视觉表示转换为离散的视觉标记，通过向量数据库实现高效识别，并在UA-DETRAC数据集上展示了有效的性能。 AI

影响这种方法可以在无需大量重新训练的情况下，实现更灵活和可扩展的目标识别系统。

排序理由该集群包含一篇详细介绍目标检测和分割新方法的学术论文。

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]

arXiv cs.AI TIER_1 English(EN) · ZhiXin Sun · 2026-07-10 04:00

VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Tokenization and Vector Database Retrieval

arXiv:2607.08541v1 Announce Type: cross Abstract: Open-vocabulary object detection and segmentation aim to recognize arbitrary objects beyond predefined categories. Although recent vision-language and reference-based approaches have significantly advanced this field, they often r…
arXiv cs.AI TIER_1 English(EN) · ZhiXin Sun · 2026-07-09 14:35

VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Tokenization and Vector Database Retrieval

Open-vocabulary object detection and segmentation aim to recognize arbitrary objects beyond predefined categories. Although recent vision-language and reference-based approaches have significantly advanced this field, they often rely on text prompts, limited visual examples, or e…