Deep neural networks excel in supervised learning tasks but are constrained by the need for
extensive labeled data. Self-supervised learning emerges as a promising alternative …

Unsupervised pre-training methods for large vision models have shown to enhance
performance on downstream supervised tasks. Developing similar techniques for satellite …

Neural compression is the application of neural networks and other machine learning
methods to data compression. Recent advances in statistical machine learning have opened …

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 …

This paper investigates task-oriented communication for multi-device cooperative edge
inference, where a group of distributed low-end edge devices transmit the extracted features …

Although deep learning has made great progress in recent years, the exploding economic
and environmental costs of training neural networks are becoming unsustainable. To …

There has been much interest in deploying deep learning algorithms on low-powered
devices, including smartphones, drones, and medical sensors. However, full-scale deep …

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 …

The development of CLIP [Radford et al., 2021] has sparked a debate on whether language
supervision can result in vision models with more transferable representations than …

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 …