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 …

Self-supervised representation learning (SSRL) methods aim to provide powerful, deep
feature learning without the requirement of large annotated data sets, thus alleviating the …

The recent breakthroughs in natural language processing for model pretraining on large
quantities of data have opened the way for similar foundation models in computer vision …

Quantitative evaluation of tissue images is crucial for computational pathology (CPath) tasks,
requiring the objective characterization of histopathological entities from whole-slide images …

How does one adapt a pre-trained visual model to novel downstream tasks without task-
specific finetuning or any model modification? Inspired by prompting in NLP, this paper …

Abstract We propose Masked Siamese Networks (MSN), a self-supervised learning
framework for learning image representations. Our approach matches the representation of …

Recent work has shown that self-supervised pre-training leads to improvements over
supervised learning on challenging visual recognition tasks. CLIP, an exciting new …

Few-shot learning (FSL) is an important and topical problem in computer vision that has
motivated extensive research into numerous methods spanning from sophisticated meta …

Visual recognition is recently learned via either supervised learning on human-annotated
image-label data or language-image contrastive learning with webly-crawled image-text …

Mainstream 3D representation learning approaches are built upon contrastive or generative
modeling pretext tasks, where great improvements in performance on various downstream …