Joint-embedding based learning (e.g., SimCLR, MoCo, DINO) and
reconstruc...
We introduce new methods for 1) accelerating and 2) stabilizing training...
Self-supervised learning, dubbed the dark matter of intelligence, is a
p...
Recent state-of-the-art vision models introduced new architectures, lear...
Deep learning has led to remarkable advances in computer vision. Even so...
As datasets and models become increasingly large, distributed training h...
Vision Transformers (ViT) have recently emerged as a powerful alternativ...
Convolutional architectures have proven extremely successful for vision
...
Methods for understanding the decisions of and mechanisms underlying dee...
Representational sparsity is known to affect robustness to input
perturb...
Humans can learn and reason under substantial uncertainty in a space of
...
Recent advances in deep reinforcement learning require a large amount of...
Class selectivity, typically defined as how different a neuron's respons...
We seek to learn a representation on a large annotated data source that
...
Convolutional neural networks trained without supervision come close to
...
We present Decentralized Distributed Proximal Policy Optimization (DD-PP...
We analyze the dynamics of training deep ReLU networks and their implica...