Astounding results from Transformer models on natural language tasks have intrigued the
vision community to study their application to computer vision problems. Among their salient …

Recently, the proposed deep multilayer perceptron (MLP) models have stirred up a lot of
interest in the vision community. Historically, the availability of larger datasets combined with …

Abstract Vision Transformers (ViTs) and their multi-scale and hierarchical variations have
been successful at capturing image representations but their use has been generally …

The mainstream paradigm behind continual learning has been to adapt the model
parameters to non-stationary data distributions, where catastrophic forgetting is the central …

Compute, data, and algorithmic advances are the three fundamental factors that drive
progress in modern Machine Learning (ML). In this paper we study trends in the most readily …

In this paper, we present Uformer, an effective and efficient Transformer-based architecture
for image restoration, in which we build a hierarchical encoder-decoder network using the …

Panoptic segmentation assigns semantic and instance ID labels to every pixel of an image.
As permutations of instance IDs are also valid solutions, the task requires learning of high …

Transformer, first applied to the field of natural language processing, is a type of deep neural
network mainly based on the self-attention mechanism. Thanks to its strong representation …

Hyperspectral image (HSI) classification is an important task in earth observation missions.
Convolution neural networks (CNNs) with the powerful ability of feature extraction have …

While features of different scales are perceptually important to visual inputs, existing vision
transformers do not yet take advantage of them explicitly. To this end, we first propose a …