research
∙
04/25/2023
Objectives Matter: Understanding the Impact of Self-Supervised Objectives on Vision Transformer Representations
Joint-embedding based learning (e.g., SimCLR, MoCo, DINO) and reconstruc...
share
research
∙
04/25/2023
Stable and low-precision training for large-scale vision-language models
We introduce new methods for 1) accelerating and 2) stabilizing training...
research
∙
04/24/2023
A Cookbook of Self-Supervised Learning
Self-supervised learning, dubbed the dark matter of intelligence, is a p...
research
∙
10/24/2022
The Robustness Limits of SoTA Vision Models to Natural Variation
Recent state-of-the-art vision models introduced new architectures, lear...
research
∙
10/24/2022
Robust Self-Supervised Learning with Lie Groups
Deep learning has led to remarkable advances in computer vision. Even so...
research
∙
10/15/2021
Trade-offs of Local SGD at Scale: An Empirical Study
As datasets and models become increasingly large, distributed training h...
research
∙
06/10/2021
Transformed CNNs: recasting pre-trained convolutional layers with self-attention
Vision Transformers (ViT) have recently emerged as a powerful alternativ...
research
∙
03/19/2021
ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
Convolutional architectures have proven extremely successful for vision ...
research
∙
10/22/2020
Towards falsifiable interpretability research
Methods for understanding the decisions of and mechanisms underlying dee...
research
∙
10/14/2020
Linking average- and worst-case perturbation robustness via class selectivity and dimensionality
Representational sparsity is known to affect robustness to input perturb...
research
∙
10/06/2020
CURI: A Benchmark for Productive Concept Learning Under Uncertainty
Humans can learn and reason under substantial uncertainty in a space of ...
research
∙
03/12/2020
Analyzing Visual Representations in Embodied Navigation Tasks
Recent advances in deep reinforcement learning require a large amount of...
research
∙
03/03/2020
Selectivity considered harmful: evaluating the causal impact of class selectivity in DNNs
Class selectivity, typically defined as how different a neuron's respons...
research
∙
02/26/2020
Representation Learning Through Latent Canonicalizations
We seek to learn a representation on a large annotated data source that ...
research
∙
01/10/2020
Pruning Convolutional Neural Networks with Self-Supervision
Convolutional neural networks trained without supervision come close to ...
research
∙
11/01/2019
Decentralized Distributed PPO: Solving PointGoal Navigation
We present Decentralized Distributed Proximal Policy Optimization (DD-PP...
research
∙
05/31/2019