The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by
its unnormalized (log-) probabilities. Over the past years, the machine learning community …

Edge computing and artificial intelligence (AI), especially deep learning algorithms, are
gradually intersecting to build the novel system, namely edge intelligence. However, the …

We introduce A-ViT, a method that adaptively adjusts the inference cost of vision transformer
ViT for images of different complexity. A-ViT achieves this by automatically reducing the …

Dynamic neural network is an emerging research topic in deep learning. Compared to static
models which have fixed computational graphs and parameters at the inference stage …

Rotated object detection aims to identify and locate objects in images with arbitrary
orientation. In this scenario, the oriented directions of objects vary considerably across …

Built on top of self-attention mechanisms, vision transformers have demonstrated
remarkable performance on a variety of vision tasks recently. While achieving excellent …

The performance of video prediction has been greatly boosted by advanced deep neural
networks. However, most of the current methods suffer from large model sizes and require …

Convolutional neural networks have been widely deployed in various application scenarios.
In order to extend the applications' boundaries to some accuracy-crucial domains …

As an essential problem in computer vision, salient object detection (SOD) has attracted an
increasing amount of research attention over the years. Recent advances in SOD are …

Abstract Vision Transformers (ViT) have achieved remarkable success in large-scale image
recognition. They split every 2D image into a fixed number of patches, each of which is …