研究人员推出FungiTastic，一个新颖的无训练框架，用于细粒度蘑菇语义分割，特别是在低数据量场景下。该两阶段方法首先使用SAM3通过宏分类提示进行类无关掩码，然后使用DINOv3通过原型匹配进行细粒度标注。与类特定提示相比，该方法提供了可扩展性和效率，为这项具有挑战性的任务建立了一个新基线。 AI
影响 为低数据量设置下的细粒度分割奠定了基线，可能适用于其他细分领域分类任务。
排序理由 该集群包含一篇详细介绍特定计算机视觉任务新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.22492v1 Announce Type: new Abstract: Fine-grained semantic segmentation requires both precise localization and discrimination between visually similar classes. In FungiTastic, this problem is further complicated by a long-tailed distribution and strong variation in ima…
Fine-grained semantic segmentation requires both precise localization and discrimination between visually similar classes. In FungiTastic, this problem is further complicated by a long-tailed distribution and strong variation in image acquisition conditions. We propose a training…