Convolutional neural networks (CNN) have recently shown outstanding image classification
performance in the large-scale visual recognition challenge (ILSVRC2012). The success of …

Successful visual object recognition methods typically rely on training datasets containing
lots of richly annotated images. Annotating object bounding boxes is both expensive and …

To unlock video chat for hundreds of millions of people hindered by poor connectivity or
unaffordable data costs, we propose to authentically reconstruct faces on the receiver's device …

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. These …

The goal of two-sample tests is to assess whether two samples, $S_P \sim P^n$ and $S_Q \sim
Q^m$, are drawn from the same distribution. Perhaps intriguingly, one relatively …

We aim to localize objects in images using image-level supervision only. Previous approaches
to this problem mainly focus on discriminative object regions and often fail to locate …

Transformers have recently emerged as a powerful tool for learning visual representations. In
this paper, we identify and characterize artifacts in feature maps of both supervised and self…

Successful visual object recognition methods typically rely on training datasets containing
lots of richly annotated images. Annotating object bounding boxes is both expensive and …

This paper introduces submodel co-training, a regularization method related to co-training,
self-distillation and stochastic depth. Given a neural network to be trained, for each sample …

A sentence is more than the sum of its words: its meaning depends on how they combine with
one another. The brain mechanisms underlying such semantic composition remain poorly …