AI RESEARCH
End-to-end Feature Alignment: A Simple CNN with Intrinsic Class Attribution
arXiv CS.CV
•
ArXi:2603.25798v1 Announce Type: new We present Feature-Align CNN (FA-CNN), a prototype CNN architecture with intrinsic class attribution through end-to-end feature alignment. Our intuition is that the use of unordered operations such as Linear and Conv2D layers cause unnecessary shuffling and mixing of semantic concepts, thereby making raw feature maps difficult to understand. We