Conditional 3D generation is undergoing a significant advancement, enabl...
Geometry and color information provided by the point clouds are both cru...
The excellent performance of deep neural networks is usually accompanied...
Knowledge distillation conducts an effective model compression method wh...
Training a 3D scene understanding model requires complicated human
annot...
Rapidly learning from ongoing experiences and remembering past events wi...
Mainstream 3D representation learning approaches are built upon contrast...
The success of deep learning heavily relies on large-scale data with
com...
Learning descriptive 3D features is crucial for understanding 3D scenes ...
The deep learning (DL)-based methods of low-level tasks have many advant...
The success of deep learning is usually accompanied by the growth in neu...
Computing-in-memory (CiM) is a promising technique to achieve high energ...
A data augmentation module is utilized in contrastive learning to transf...
Recent progress in image-to-image translation has witnessed the success ...
The remarkable breakthroughs in point cloud representation learning have...
Collecting paired training data is difficult in practice, but the unpair...
The Chan-Vese (CV) model is a classic region-based method in image
segme...
Multi-chip integration is widely recognized as the extension of Moore's ...
Remarkable achievements have been attained with Generative Adversarial
N...
Quantized neural networks typically require smaller memory footprints an...
Most feedforward convolutional neural networks spend roughly the same ef...
Continual learning aims to learn a sequence of tasks from dynamic data
d...
Weight pruning is a powerful technique to realize model compression. We
...
Weight pruning has been widely acknowledged as a straightforward and
eff...
Existing domain adaptation methods aim at learning features that can be
...
Many existing interpretation methods of convolutional neural networks (C...
Model compression techniques on Deep Neural Network (DNN) have been wide...
Large deep neural network (DNN) models pose the key challenge to energy
...
A human does not have to see all elephants to recognize an animal as an
...
Convolutional neural networks have been widely deployed in various
appli...
Weight quantization is one of the most important techniques of Deep Neur...
It is well known that deep neural networks (DNNs) are vulnerable to
adve...