Hard negative mixing for contrastive learning
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 …
for computer vision. By learning to embed two augmented versions of the same image close …
Csi: Novelty detection via contrastive learning on distributionally shifted instances
Novelty detection, ie, identifying whether a given sample is drawn from outside the training
distribution, is essential for reliable machine learning. To this end, there have been many …
distribution, is essential for reliable machine learning. To this end, there have been many …
What to hide from your students: Attention-guided masked image modeling
Transformers and masked language modeling are quickly being adopted and explored in
computer vision as vision transformers and masked image modeling (MIM). In this work, we …
computer vision as vision transformers and masked image modeling (MIM). In this work, we …
Subtab: Subsetting features of tabular data for self-supervised representation learning
T Ucar, E Hajiramezanali… - Advances in Neural …, 2021 - proceedings.neurips.cc
Self-supervised learning has been shown to be very effective in learning useful
representations, and yet much of the success is achieved in data types such as images …
representations, and yet much of the success is achieved in data types such as images …
Review on self-supervised image recognition using deep neural networks
Deep learning has brought significant developments in image understanding tasks such as
object detection, image classification, and image segmentation. But the success of image …
object detection, image classification, and image segmentation. But the success of image …
Sequence-to-sequence contrastive learning for text recognition
We propose a framework for sequence-to-sequence contrastive learning (SeqCLR) of visual
representations, which we apply to text recognition. To account for the sequence-to …
representations, which we apply to text recognition. To account for the sequence-to …
[HTML][HTML] Self-supervised representation learning from 12-lead ECG data
T Mehari, N Strodthoff - Computers in biology and medicine, 2022 - Elsevier
Abstract Clinical 12-lead electrocardiography (ECG) is one of the most widely encountered
kinds of biosignals. Despite the increased availability of public ECG datasets, label scarcity …
kinds of biosignals. Despite the increased availability of public ECG datasets, label scarcity …
The causal-neural connection: Expressiveness, learnability, and inference
One of the central elements of any causal inference is an object called structural causal
model (SCM), which represents a collection of mechanisms and exogenous sources of …
model (SCM), which represents a collection of mechanisms and exogenous sources of …
Robust contrastive learning against noisy views
Contrastive learning relies on an assumption that positive pairs contain related views that
share certain underlying information about an instance, eg, patches of an image or co …
share certain underlying information about an instance, eg, patches of an image or co …
Perfectly balanced: Improving transfer and robustness of supervised contrastive learning
An ideal learned representation should display transferability and robustness. Supervised
contrastive learning (SupCon) is a promising method for training accurate models, but …
contrastive learning (SupCon) is a promising method for training accurate models, but …