Fine-grained image recognition is a longstanding computer vision challen...
Over the past decade, deep learning models have exhibited considerable
a...
We prove that the single-site Glauber dynamics for sampling proper
q-col...
Early exiting has become a promising approach to improving the inference...
Rotated object detection aims to identify and locate objects in images w...
Large deep learning models have achieved remarkable success in many
scen...
The superior performance of modern deep networks usually comes at the pr...
Recent research has revealed that reducing the temporal and spatial
redu...
Extensive studies on Unsupervised Domain Adaptation (UDA) have propelled...
Spatial redundancy widely exists in visual recognition tasks, i.e.,
disc...
Recent works have shown that the computational efficiency of video
recog...
Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a
l...
Vision Transformers (ViT) have achieved remarkable success in large-scal...
In this paper, we explore the spatial redundancy in video recognition wi...
Reusing features in deep networks through dense connectivity is an effec...
Real-world training data usually exhibits long-tailed distribution, wher...
Domain adaptation has been widely explored by transferring the knowledge...
Dynamic neural network is an emerging research topic in deep learning.
C...
Due to the need to store the intermediate activations for back-propagati...
The accuracy of deep convolutional neural networks (CNNs) generally impr...
Data augmentation is widely known as a simple yet surprisingly effective...
Deep learning based semi-supervised learning (SSL) algorithms have led t...
In this paper, we propose a novel implicit semantic data augmentation (I...