2 papers
cs.CV2026
Why CNN Features Are not Gaussian: A Statistical Anatomy of Deep Representations
David Chapman, Parniyan Farvardin
Deep convolutional neural networks (CNNs) are commonly analyzed through geometric and linear-algebraic perspectives, yet the statistical distribution of their internal feature acti…
cs.CV2026
End-to-end Feature Alignment: A Simple CNN with Intrinsic Class Attribution
Parniyan Farvardin, David Chapman
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 unordere…