research
∙
07/25/2023
How to Scale Your EMA
Preserving training dynamics across batch sizes is an important tool for...
share
research
∙
07/20/2023
The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning
The mechanisms behind the success of multi-view self-supervised learning...
research
∙
06/28/2023
DUET: 2D Structured and Approximately Equivariant Representations
Multiview Self-Supervised Learning (MSSL) is based on learning invarianc...
research
∙
03/11/2023
Stabilizing Transformer Training by Preventing Attention Entropy Collapse
Training stability is of great importance to Transformers. In this work,...
research
∙
10/28/2022
Elastic Weight Consolidation Improves the Robustness of Self-Supervised Learning Methods under Transfer
Self-supervised representation learning (SSL) methods provide an effecti...
research
∙
07/15/2022
Position Prediction as an Effective Pretraining Strategy
Transformers have gained increasing popularity in a wide range of applic...
research
∙
11/24/2021
Challenges of Adversarial Image Augmentations
Image augmentations applied during training are crucial for the generali...
research
∙
10/01/2021
Stochastic Contrastive Learning
While state-of-the-art contrastive Self-Supervised Learning (SSL) models...
research
∙
10/01/2021
Evaluating the fairness of fine-tuning strategies in self-supervised learning
In this work we examine how fine-tuning impacts the fairness of contrast...
research
∙
10/01/2021
Do Self-Supervised and Supervised Methods Learn Similar Visual Representations?
Despite the success of a number of recent techniques for visual self-sup...
research
∙
02/20/2021
Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory
Episodic and semantic memory are critical components of the human memory...
research
∙
06/29/2020
Self-Supervised MultiModal Versatile Networks
Videos are a rich source of multi-modal supervision. In this work, we le...
research
∙
05/09/2019
Differentiable Approximation Bridges For Training Networks Containing Non-Differentiable Functions
Modern neural network training relies on piece-wise (sub-)differentiable...
research
∙
12/08/2018
Variational Saccading: Efficient Inference for Large Resolution Images
Image classification with deep neural networks is typically restricted t...
research
∙
10/24/2018
Continual Classification Learning Using Generative Models
Continual learning is the ability to sequentially learn over time by acc...
research
∙
06/30/2018
A New Benchmark and Progress Toward Improved Weakly Supervised Learning
Knowledge Matters: Importance of Prior Information for Optimization [7],...
research
∙
04/19/2018
Large-scale Nonlinear Variable Selection via Kernel Random Features
We propose a new method for input variable selection in nonlinear regres...
research
∙
05/27/2017