研究人员推出了一种用于计算机视觉中即时类别发现的新颖框架DP-BOA。该方法利用具有正态-逆Wishart先验的在线狄利克雷过程高斯混合模型，明确比较将样本分配给现有类别与生成新类别的证据。DP-BOA在标准的OCD基准测试中表现出色，尤其是在发现新类别同时保持已知类别准确性方面。 AI
影响 该方法可以提高AI系统在无需显式重新训练的情况下适应新类别的能力。
排序理由 该集群包含一篇详细介绍类别发现新方法的论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
On-the-fly category discovery requires deciding for each incoming test sample whether to assign it to an existing category or spawn a new one. Existing methods typically implement this decision through matching-based heuristics, such as radius- or hash-based rules. While effectiv…
arXiv:2607.13504v1 Announce Type: new Abstract: On-the-fly category discovery requires deciding for each incoming test sample whether to assign it to an existing category or spawn a new one. Existing methods typically implement this decision through matching-based heuristics, suc…
On-the-fly category discovery requires deciding for each incoming test sample whether to assign it to an existing category or spawn a new one. Existing methods typically implement this decision through matching-based heuristics, such as radius- or hash-based rules. While effectiv…