Despite the importance of image representations such as histograms of oriented gradients
and deep Convolutional Neural Networks (CNN), our theoretical understanding of them …

Inner product-based convolution has been a central component of convolutional neural
networks (CNNs) and the key to learning visual representations. Inspired by the observation …

Convolutional neural networks (CNNs) are inherently limited to model geometric
transformations due to the fixed geometric structures in its building modules. In this work, we …

A fundamental problem in object recognition is the development of image representations
that are invariant to common transformations such as translation, rotation, and small …

Translating or rotating an input image should not affect the results of many computer vision
tasks. Convolutional neural networks (CNNs) are already translation equivariant: input …

We propose a general framework called Network Dissection for quantifying the
interpretability of latent representations of CNNs by evaluating the alignment between …

How can prior knowledge on the transformation invariances of a domain be incorporated
into the architecture of a neural network? We propose Equivariant Transformers (ETs), a …

Feature representations, both hand-designed and learned ones, are often hard to analyze
and interpret, even when they are extracted from visual data. We propose a new approach to …

The success of recent deep convolutional neural networks (CNNs) depends on learning
hidden representations that can summarize the important factors of variation behind the …

Abstract Implicit Neural Representations (INR) use multilayer perceptrons to represent high-
frequency functions in low-dimensional problem domains. Recently these representations …