This paper presents miCSE, a mutual information-based Contrastive learni...
Machine learning systems are often deployed in domains that entail data ...
In this paper, we propose Self-Contrastive Decorrelation (SCD), a
self-s...
Self-supervised learning has recently attracted considerable attention i...
Can we get existing language models and refine them for zero-shot common...
Although providing exceptional results for many computer vision tasks,
s...
The task of zero-shot learning (ZSL) requires correctly predicting the l...
We propose a self-supervised method to solve Pronoun Disambiguation and
...
In this paper, we propose a self-supervised learning approach that lever...
Deep Learning models have become the dominant approach in several areas ...
Automatic question generation aims at the generation of questions from a...
The recently introduced BERT model exhibits strong performance on severa...
Multi-Domain Learning (MDL) refers to the problem of learning a set of m...
Models trained in the context of continual learning (CL) should be able ...
Since the advent of deep learning, neural networks have demonstrated
rem...
State-of-the-art deep learning algorithms yield remarkable results in ma...
We introduce MASSES, a simple evaluation metric for the task of Visual
Q...
State-of-the-art deep learning algorithms generally require large amount...
Multivariate regression models for age estimation are a powerful tool fo...
Federated learning is a recent advance in privacy protection. In this
co...
With the availability of big medical image data, the selection of an ade...
We introduce DeepNAT, a 3D Deep convolutional neural network for the
aut...