Weakly supervised semantic segmentation produces pixel-level localization from class
labels; however, a classifier trained on such labels is likely to focus on a small discriminative …

Abstract Graph Neural Networks (GNNs) have shown promising results on a broad spectrum
of applications. Most empirical studies of GNNs directly take the observed graph as input …

Despite the empirical successes of self-supervised learning (SSL) methods, it is unclear
what characteristics of their representations lead to high downstream accuracies. In this …

Brain-inspired computing technique presents a promising approach to prompt the rapid
development of artificial general intelligence (AGI). As one of the most critical aspects …

Most data is automatically collected and only ever" seen" by algorithms. Yet, data
compressors preserve perceptual fidelity rather than just the information needed by …

Machine learning systems often experience a distribution shift between training and testing.
In this paper, we introduce a simple variational objective whose optima are exactly the set of …

Learning effective visual representations that generalize well without human supervision is a
fundamental problem in order to apply Machine Learning to a wide variety of tasks …

Since the introduction of deep learning, a wide scope of representation properties, such as
decorrelation, whitening, disentanglement, rank, isotropy, and mutual information, have …

Table filling based joint named entity recognition and relation extraction task aims to share
representation of subtasks in a table to extract structured knowledge. However, most of …

A major challenge in designing efficient statistical supervised learning algorithms is finding
representations that perform well not only on available training samples but also on unseen …