On the opportunities and risks of foundation models

R Bommasani, DA Hudson, E Adeli, R Altman… - arxiv preprint arxiv …, 2021 - arxiv.org
AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

Barlow twins: Self-supervised learning via redundancy reduction

J Zbontar, L **g, I Misra, Y LeCun… - … on machine learning, 2021 - proceedings.mlr.press
Self-supervised learning (SSL) is rapidly closing the gap with supervised methods on large
computer vision benchmarks. A successful approach to SSL is to learn embeddings which …

Hard negative mixing for contrastive learning

Y Kalantidis, MB Sariyildiz, N Pion… - Advances in neural …, 2020 - proceedings.neurips.cc
Contrastive learning has become a key component of self-supervised learning approaches
for computer vision. By learning to embed two augmented versions of the same image close …

Beyond just vision: A review on self-supervised representation learning on multimodal and temporal data

S Deldari, H Xue, A Saeed, J He, DV Smith… - arxiv preprint arxiv …, 2022 - arxiv.org
Recently, Self-Supervised Representation Learning (SSRL) has attracted much attention in
the field of computer vision, speech, natural language processing (NLP), and recently, with …

Provable guarantees for self-supervised deep learning with spectral contrastive loss

JZ HaoChen, C Wei, A Gaidon… - Advances in Neural …, 2021 - proceedings.neurips.cc
Recent works in self-supervised learning have advanced the state-of-the-art by relying on
the contrastive learning paradigm, which learns representations by pushing positive pairs, or …

How well do self-supervised models transfer?

L Ericsson, H Gouk… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Self-supervised visual representation learning has seen huge progress recently, but no
large scale evaluation has compared the many models now available. We evaluate the …

Whitening for self-supervised representation learning

A Ermolov, A Siarohin, E Sangineto… - … on machine learning, 2021 - proceedings.mlr.press
Most of the current self-supervised representation learning (SSL) methods are based on the
contrastive loss and the instance-discrimination task, where augmented versions of the …

An overview of deep learning techniques for epileptic seizures detection and prediction based on neuroimaging modalities: Methods, challenges, and future works

A Shoeibi, P Moridian, M Khodatars… - Computers in biology …, 2022 - Elsevier
Epilepsy is a disorder of the brain denoted by frequent seizures. The symptoms of seizure
include confusion, abnormal staring, and rapid, sudden, and uncontrollable hand …

From canonical correlation analysis to self-supervised graph neural networks

H Zhang, Q Wu, J Yan, D Wipf… - Advances in Neural …, 2021 - proceedings.neurips.cc
We introduce a conceptually simple yet effective model for self-supervised representation
learning with graph data. It follows the previous methods that generate two views of an input …

Intriguing properties of contrastive losses

T Chen, C Luo, L Li - Advances in Neural Information …, 2021 - proceedings.neurips.cc
We study three intriguing properties of contrastive learning. First, we generalize the standard
contrastive loss to a broader family of losses, and we find that various instantiations of the …