inductive priors

FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes

We provide a high bandwidth, alias-free convolutional kernel parameterization with learnable kernel size and constant parameter cost.

VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges

We present the first edition of "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" challenges. We offer four data-impaired challenges to encourage data efficient solutions.

Deep Hough-Transform Line Priors

We add line priors through a trainable Hough transform block into a deep network.

On Translation Invariance in CNNs: Convolutional Layers Can Exploit Absolute Spatial Location

We show we can prevent CNNs from exploiting absolute location through image boundary effects.