重新思考基于原型的小样本目标检测相似性学习
Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection
AI总结：
针对小样本目标检测中基于原型的方法存在类间混淆和定位线索不足的问题，提出文本锚定语义掩码和层级自回归回归，在COCO上提升10.1 nAP。
摘要：
小样本目标检测旨在仅从少量标注样本中检测新目标类别，避免昂贵的大规模标注。最近的基于原型的相似性学习方法通过将查询特征与类别原型匹配，实现了无需训练的适应。然而，它们存在两个根本性限制：(i) 类间相似性边界坍塌导致的类混淆，以及(ii) 定位所需的视觉线索不足，因为相似性分数仅捕获类别级语义亲和性，而提供有限的空间信息。为解决这些问题，我们引入了两个互补组件。文本锚定语义掩码（TSMa）利用类别级文本特征作为语义锚点，通过视觉和文本特征之间的通道交互来识别语义对齐的通道。通过抑制风格引起的虚假响应并强调类别固有信号，TSMa扩大了类间相似性边界并缓解了类混淆。我们进一步提出了阶段对齐层级自回归回归（SHARe），它将定位重新表述为一个层级自回归过程，在多个阶段逐步细化边界框。SHARe通过将特征抽象级别与回归阶段对齐，利用ViT表示的逐层特性：深层指导早期粗略定位，而富含边缘和纹理线索的浅层在后期阶段细化空间细节。在COCO上的实验表明，该方法达到了新的最先进水平，比之前的最佳方法高出10.1 nAP，广泛的分析验证了每个组件的有效性。代码可在https://this URL获取。
英文摘要：
Few-shot object detection aims to detect novel object categories from only a few labeled examples, avoiding costly large-scale annotation. Recent prototype-based similarity learning approaches enable training-free adaptation by matching query features with class prototypes. However, they suffer from two fundamental limitations: (i) class confusion arising from inter-class similarity margin collapse, and (ii) insufficient visual cues for precise localization, as similarity scores capture only class-level semantic affinity while providing limited spatial information. To address these issues, we introduce two complementary components. Text-Anchored Semantic Mask (TSMa) leverages class-level text features as semantic anchors to identify semantically aligned channels through channel-wise interaction between visual and text features. By suppressing style-induced spurious responses and emphasizing class-intrinsic signals, TSMa enlarges inter-class similarity margins and mitigates class confusion. We further propose Stage-Aligned Hierarchical Autoregressive Regression (SHARe), which reformulates localization as a hierarchical autoregressive process that progressively refines bounding boxes across multiple stages. SHARe leverages the layer-wise characteristics of ViT representations by aligning feature abstraction levels with regression stages: deeper layers guide early coarse localization, while shallower layers rich in edge and texture cues refine spatial details in later stages. Experiments on COCO demonstrate a new state of the art, outperforming the previous best by +10.1 nAP, with extensive analysis validating each component. The code is available at https://github.com/VisualScienceLab-KHU/ReSet.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
