35 citations · 138 across the 12 of their papers we have counts for
12 papers
FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models
Zhanwei Zhang, Shizhao Sun, Wenxiao Wang +2
Recently, there is a growing interest in creating computer-aided design (CAD) models based on user intent, known as controllable CAD generation. Existing work offers limited contro…
Img2Vec: A Teacher of High Token-Diversity Helps Masked AutoEncoders
Heng Pan, Chenyang Liu, Wenxiao Wang +4
We present a pipeline of Image to Vector (Img2Vec) for masked image modeling (MIM) with deep features. To study which type of deep features is appropriate for MIM as a learning tar…
Neural Collapse Inspired Federated Learning with Non-iid Data
Chenxi Huang, Liang Xie, Yibo Yang +3
One of the challenges in federated learning is the non-independent and identically distributed (non-iid) characteristics between heterogeneous devices, which cause significant diff…
One-shot Implicit Animatable Avatars with Model-based Priors
Yangyi Huang, Hongwei Yi, Weiyang Liu +6
Existing neural rendering methods for creating human avatars typically either require dense input signals such as video or multi-view images, or leverage a learned prior from large…
Towards In-distribution Compatibility in Out-of-distribution Detection
Boxi Wu, Jie Jiang, Haidong Ren +7
Deep neural network, despite its remarkable capability of discriminating targeted in-distribution samples, shows poor performance on detecting anomalous out-of-distribution data. T…
Masked Autoencoders for Point Cloud Self-supervised Learning
Yatian Pang, Wenxiao Wang, Francis E. H. Tay +3
As a promising scheme of self-supervised learning, masked autoencoding has significantly advanced natural language processing and computer vision. Inspired by this, we propose a ne…
Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training
Shuai Zhao, Liguang Zhou, Wenxiao Wang +3
The width of a neural network matters since increasing the width will necessarily increase the model capacity. However, the performance of a network does not improve linearly with…
Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
Wenxiao Wang, Minghao Chen, Shuai Zhao +6
Most neural network pruning methods, such as filter-level and layer-level prunings, prune the network model along one dimension (depth, width, or resolution) solely to meet a compu…
Boundary-Aware Dense Feature Indicator for Single-Stage 3D Object Detection from Point Clouds
Guodong Xu, Wenxiao Wang, Zili Liu +4
3D object detection based on point clouds has become more and more popular. Some methods propose localizing 3D objects directly from raw point clouds to avoid information loss. How…
DBP: Discrimination Based Block-Level Pruning for Deep Model Acceleration
Wenxiao Wang, Shuai Zhao, Minghao Chen +3
Neural network pruning is one of the most popular methods of accelerating the inference of deep convolutional neural networks (CNNs). The dominant pruning methods, filter-level pru…
The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks
Yuheng Zhang, Ruoxi Jia, Hengzhi Pei +3
This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have r…
COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning
Wenxiao Wang, Cong Fu, Jishun Guo +2
Neural network compression empowers the effective yet unwieldy deep convolutional neural networks (CNN) to be deployed in resource-constrained scenarios. Most state-of-the-art appr…