Contrastive Learning

When a neural network learns image labels, it may confuse a background item for the labeled object. New research avoids such mistakes.

Images in the wild may not come with labels, but they often include metadata. A new training method takes advantage of this information to improve contrastive learning.

Pretraining methods generate basic representations for later fine-tuning, but they’re prone to certain issues that can throw them off-kilter. New work proposes a solution.

It’s expensive to pay doctors to label medical images, and the relative scarcity of high-quality training examples can make it hard for neural networks to learn features that make for accurate diagnoses.

For people with neurological disorders like epilepsy, attaching sensors to the scalp to measure electrical currents within the brain is benign. But interpreting the resulting electroencephalogram (EEG) graphs can give doctors a headache.

Which comes first, training a reinforcement learning model or extracting high-quality features? New work avoids this chicken-or-egg dilemma by doing both simultaneously.

A simple linear classifier paired with a self-supervised feature extractor outperformed a supervised deep learning model on ImageNet, according to new research.