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 popularity of machine learning (ML), deep learning (DL) and artificial intelligence (AI)
has risen sharply in recent years. Despite this spike in popularity, the inner workings of ML …

Abstract Out-of-distribution (OOD) detection is a critical task for deploying machine learning
models in the open world. Distance-based methods have demonstrated promise, where …

This paper demonstrates an approach for learning highly semantic image representations
without relying on hand-crafted data-augmentations. We introduce the Image-based Joint …

Abstract A Vision Transformer (ViT) is a simple neural architecture amenable to serve
several computer vision tasks. It has limited built-in architectural priors, in contrast to more …

This paper shows that masked autoencoders (MAE) are scalable self-supervised learners
for computer vision. Our MAE approach is simple: we mask random patches of the input …

Deep long-tailed learning, one of the most challenging problems in visual recognition, aims
to train well-performing deep models from a large number of images that follow a long-tailed …

Abstract Out-of-distribution (OOD) detection has received much attention lately due to its
practical importance in enhancing the safe deployment of neural networks. One of the …

Most of the existing Out-Of-Distribution (OOD) detection algorithms depend on single input
source: the feature, the logit, or the softmax probability. However, the immense diversity of …

Recent image generation models such as Stable Diffusion have exhibited an impressive
ability to generate fairly realistic images starting from a simple text prompt. Could such …