通过部分分解注意力的空间基础概念瓶颈模型
Spatially Grounded Concept Bottleneck Models via Part-Factorized Attention
AI总结：
提出一种部分分解的概念瓶颈模型，通过空间先验约束注意力，在细粒度识别中实现可解释性并提升定位精度。
摘要：
概念瓶颈模型（CBM）在预测类别之前预测一层人类命名的属性，从而使其决策可审计。在细粒度识别任务中，概念头通常可以自由关注图像中的任何位置，因此以某个身体区域命名的头可能被其他区域的证据满足。本研究通过构造一个部分分解的CBM来消除这种自由度。该方法基于冻结的DINOv3视觉变换器，包含三个组件。一个学习到的前景门控，基于DINOv3块特征训练，抑制部分注意力内的背景块。一组部分查询交叉关注块特征，并且312个CUB属性中的每一个通过固定的概念到部分映射被路由，仅从其名称所暗示的部分令牌读取。一个可学习的二维高斯先验，以对数空间加性注入注意力logits，打破部分查询之间的排列对称性；其均值从每个部分的数据集平均关键点位置初始化，在训练或测试时不需要每张图像的关键点监督。在CUB-200-2011上，空间先验模型匹配完全监督基线（top-1准确率88.85%对88.95%），同时将指向精度提高16个百分点（52.6%对36.4%）。用PCA前景目标替换边界框监督，并与高斯先验结合，消除了所有每张图像监督，达到88.6%的top-1准确率和约70%的指向精度。关键点分数扫描显示，训练集的0.5%（约27张图像）足以初始化先验，且无显著损失。完全移除部分身份是更困难的情况：没有任何空间先验，指向精度降至2.9%。
英文摘要：
Concept bottleneck models (CBMs) predict a layer of human-named attributes before predicting a class, which makes their decisions auditable. On fine-grained recognition tasks, though, the concept heads are usually free to attend anywhere in the image, so a head named for one body region can be satisfied by evidence on another, and the model reaches the right answer for the wrong reason. We propose a part-factorized CBM (PF-CBM) that removes this freedom by construction. A frozen DINOv3 vision transformer feeds a set of part queries, each tied by name to a specific anatomical region through a fixed concept-to-part map, while whole-object attributes such as size and shape are handled separately by a query with no spatial prior, since they are not anchored to any single body part. A learnable Gaussian prior over patch locations, initialized from average keypoint positions, keeps the part queries from collapsing onto the same evidence. On its own this prior spreads the queries apart but does not reliably land them on the correct anatomy. What closes that gap is a lightweight alignment loss that nudges each part query toward its keypoint, and the central finding of this paper is how little of that supervision is required. Aligning on well under one percent of the training images already moves pointing accuracy from near-chance to roughly three-quarters of what full keypoint supervision achieves, and the gains continue, more slowly, as more annotated images are added. Classification accuracy on CUB-200-2011 barely moves across this entire range and stays within a point of a fully supervised baseline whether the model sees no keypoints at all or every one of them. Grounding a CBM's attention to the right evidence turns out to be nearly free in accuracy and cheap in annotation, provided the model has the right inductive bias to make efficient use of that small amount of supervision.
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。
