Deep learning approaches to anomaly detection (AD) have recently improved the state of
the art in detection performance on complex data sets, such as large collections of images or …

Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

This paper presents SimCLR: a simple framework for contrastive learning of visual
representations. We simplify recently proposed contrastive self-supervised learning …

Contrastive learning between multiple views of the data has recently achieved state of the
art performance in the field of self-supervised representation learning. Despite its success …

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 …

Change detection (CD) aims to identify surface changes from bitemporal images. In recent
years, deep learning (DL)-based methods have made substantial breakthroughs in the field …

Semi-supervised learning, ie jointly learning from labeled and unlabeled samples, is an
active research topic due to its key role on relaxing human supervision. In the context of …

We introduce SinGAN, an unconditional generative model that can be learned from a single
natural image. Our model is trained to capture the internal distribution of patches within the …

In this paper, we propose Test-Time Training, a general approach for improving the
performance of predictive models when training and test data come from different …

In real-world classification tasks, each class often comprises multiple finer-grained"
subclasses." As the subclass labels are frequently unavailable, models trained using only …