Convolutional neural networks (CNNs) have shown great success in computer vision,
approaching human-level performance when trained for specific tasks via application …

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 …

Hierarchical feature learning based on convolutional neural networks (CNN) has recently
shown significant potential in various computer vision tasks. While allowing high-quality …

Visual recognition requires rich representations that span levels from low to high, scales
from small to large, and resolutions from fine to coarse. Even with the depth of features in a …

Deep convolutional neural networks (DCNNs) are powerful models that yield impressive
results at object classification. However, recent work has shown that they do not generalize …

In this work, we develop a novel method for automatically learning aspects of the structure of
a deep model, in order to improve its performance, especially when labeled training data are …

The remarkable successes of convolutional neural networks (CNNs) in modern computer
vision are by now well known, and they are increasingly being explored as computational …

While the use of bottom-up local operators in convolutional neural networks (CNNs)
matches well some of the statistics of natural images, it may also prevent such models from …

Compositionality and contextuality are key building blocks of intelligence. They allow us to
compose known concepts to generate new and complex ones. However, traditional learning …

One of the cornerstone principles of deep models is their abstraction capacity, ie their ability
to learn abstract concepts fromsimpler'ones. Through extensive experiments, we …