Deep learning algorithms are a subset of the machine learning algorithms, which aim at
discovering multiple levels of distributed representations. Recently, numerous deep learning …

The aim of this paper is to give an overview of domain adaptation and transfer learning with
a specific view on visual applications. After a general motivation, we first position domain …

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined
object categories. This restricted form of supervision limits their generality and usability since …

Contrastive language-image pretraining (CLIP) using image-text pairs has achieved
impressive results on image classification in both zero-shot and transfer learning settings …

The success of deep learning in vision can be attributed to:(a) models with high capacity;(b)
increased computational power; and (c) availability of large-scale labeled data. Since 2012 …

A major open problem on the road to artificial intelligence is the development of
incrementally learning systems that learn about more and more concepts over time from a …

Although deep learning approaches have stood out in recent years due to their state-of-the-
art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall …

It is always well believed that modeling relationships between objects would be helpful for
representing and eventually describing an image. Nevertheless, there has not been …

We present a theoretically grounded approach to train deep neural networks, including
recurrent networks, subject to class-dependent label noise. We propose two procedures for …

Abstract Visual Question Answering (VQA) in its ideal form lets us study reasoning in the
joint space of vision and language and serves as a proxy for the AI task of scene …