CVNets: High Performance Library for Computer Vision

3 years ago

We introduce CVNets, a high-performance open-source library for training deep neural networks for visual recognition tasks, including classification, detection, and…

FORML: Learning to Reweight Data for Fairness

3 years ago

Machine learning models are trained to minimize the mean loss for a single metric, and thus typically do not consider…

Regularized Training of Nearest Neighbor Language Models

3 years ago

Including memory banks in a natural language processing architecture increases model capacity by equipping it with additional data at inference…

A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing

3 years ago

A key algorithm for understanding the world is material segmentation, which assigns a label (metal, glass, etc.) to each pixel.…

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting

3 years ago

The practical success of overparameterized neural networks has motivated the recent scientific study of interpolating methods, which perfectly fit their…

Understanding Convolutions on Graphs

3 years ago

Understanding the building blocks and design choices of graph neural networks.

A Gentle Introduction to Graph Neural Networks

3 years ago

What components are needed for building learning algorithms that leverage the structure and properties of graphs?

Distill Hiatus

3 years ago

After five years, Distill will be taking a break.

Adversarial Reprogramming of Neural Cellular Automata

3 years ago

Reprogramming Neural CA to exhibit novel behaviour, using adversarial attacks.

Weight Banding

3 years ago

Weights in the final layer of common visual models appear as horizontal bands. We investigate how and why.