2 papers
cs.CV2026
Rethinking Global Average Pooling: Your Classifier Is Secretly a Multi-Instance Learner
Aray Karjauv
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…
cs.CV2024
LaFAM: Unsupervised Feature Attribution with Label-free Activation Maps
Aray Karjauv, Sahin Albayrak
Convolutional Neural Networks (CNNs) are known for their ability to learn hierarchical structures, naturally developing detectors for objects, and semantic concepts within their de…