无需训练，用原型匹配实现低数据下的蘑菇细粒度分割
Training-Free Fine-Grained Semantic Segmentations in Low Data Regimes: A FungiTastic Baseline
- 先用通用提示生成蘑菇掩码，再通过嵌入空间原型匹配分配细粒度标签
- 在单样本到数百样本场景下均表现稳定，首次建立低数据细粒度分割基准
- 方法无需微调，适合数据稀缺的生物分类任务
细粒度语义分割需精准定位并区分视觉相似类别。在FungiTastic中，这一问题因长尾分布和图像采集条件差异而加剧。我们提出一种无需训练的两阶段框架，将分割与分类解耦：SAM3首先使用宏观分类提示生成类无关的蘑菇掩码，DINOv3则通过嵌入空间中的原型匹配分配细粒度标签。为提升该阶段性能，我们对DINOv3特征空间施加简单变换，增强原型分类效果。相比特定类别提示，本方法更具可扩展性且保持低分割成本。我们在从单样本到数百样本的设置下报告结果，据我们所知，首次为低数据环境下的细粒度语义分割提供了基准。
原文摘要 · Abstract (English)
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-free two-stage framework that decouples segmentation from classification. SAM3 first produces class-agnostic mushroom masks using macro-taxonomic prompts, and DINOv3 then assigns fine-grained labels through prototype matching in the embedding space. To improve this stage, we apply a simple transformation of the DINOv3 feature space that improves prototype-based classification. Compared with class-specific prompting, our approach is more scalable and keeps the segmentation cost low. We report results from one-shot to few-hundred-shot regimes, providing, to the best of our knowledge, the first baseline for fine-grained semantic segmentation in low-data settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。