用GAP隐藏的空间证据诊断分类错误
这篇论文指出，现代图像分类器使用的全局平均池化（GAP）加线性分类头的结构，使图像级logits等于特征网格上逐点分类后logits的平均值。这种线性性意味着标准分类器本质上是多实例学习器（MIL），将图像视为空间实例的包。实验发现，即使图像级预测错误，分类器仍在特征网格中保留了空间类别证据，且现成模型（off-the-shelf models）能稳定恢复前景区域的地面真实类别。该研究将GAP隐藏的空间信息重新提取出来，为模型诊断提供了新思路。
Rethinking Global Average Pooling: Your Classifier Is Secretly a Multi-Instance Learner
Modern image classifiers widely adopt global average pooling (GAP) followed by a linear classification head. This linearity ensures that the image-level logits equal the average of logits obtained by applying the classification head pointwise to the feature grid prior to GAP. Consequently, standard classifiers may inherently retain spatial class evidence that remains recoverable even when the image-level prediction is incorrect. This structure naturally suggests a multiple-instance learning (MIL) interpretation, where an image is viewed as a bag of spatial instances. Within this formulation, we demonstrate that standard classifiers trained with a single label per image can still learn the intended classification task in multi-object scenes. We further exploit this property to decompose image-level logits into a prediction grid, providing a post-hoc diagnostic to extract spatial class evidence that GAP otherwise obscures. Our systematic evaluation reveals that off-the-shelf models consistently recover the ground-truth class within foreground regions. The MIL interpretation further suggests that common classifier failures reflect known limitations of mean aggregation.