Search Results for author: Siyu Liao

Found 12 papers, 0 papers with code

Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Framework

no code implementations CVPR 2021 Miao Yin, Yang Sui, Siyu Liao, Bo Yuan

Notably, on CIFAR-100, with 2. 3X and 2. 4X compression ratios, our models have 1. 96% and 2. 21% higher top-1 accuracy than the original ResNet-20 and ResNet-32, respectively.

Image Classification Model Compression +2

Towards Extremely Compact RNNs for Video Recognition with Fully Decomposed Hierarchical Tucker Structure

no code implementations CVPR 2021 Miao Yin, Siyu Liao, Xiao-Yang Liu, Xiaodong Wang, Bo Yuan

Although various prior works have been proposed to reduce the RNN model sizes, executing RNN models in resource-restricted environments is still a very challenging problem.

Tensor Decomposition Video Recognition

Noise Injection-based Regularization for Point Cloud Processing

no code implementations28 Mar 2021 Xiao Zang, Yi Xie, Siyu Liao, Jie Chen, Bo Yuan

In this paper, we, for the first time, perform systematic investigation on noise injection-based regularization for point cloud-domain DNNs.

Data Augmentation Semantic Segmentation

Doubly Residual Neural Decoder: Towards Low-Complexity High-Performance Channel Decoding

no code implementations8 Feb 2021 Siyu Liao, Chunhua Deng, Miao Yin, Bo Yuan

Recently deep neural networks have been successfully applied in channel coding to improve the decoding performance.

PERMDNN: Efficient Compressed DNN Architecture with Permuted Diagonal Matrices

no code implementations23 Apr 2020 Chunhua Deng, Siyu Liao, Yi Xie, Keshab K. Parhi, Xuehai Qian, Bo Yuan

On the other hand, the recent structured matrix-based approach (i. e., CirCNN) is limited by the relatively complex arithmetic computation (i. e., FFT), less flexible compression ratio, and its inability to fully utilize input sparsity.

Model Compression

Embedding Compression with Isotropic Iterative Quantization

no code implementations11 Jan 2020 Siyu Liao, Jie Chen, Yanzhi Wang, Qinru Qiu, Bo Yuan

Continuous representation of words is a standard component in deep learning-based NLP models.

Image Retrieval Quantization +1

CAG: A Real-time Low-cost Enhanced-robustness High-transferability Content-aware Adversarial Attack Generator

no code implementations16 Dec 2019 Huy Phan, Yi Xie, Siyu Liao, Jie Chen, Bo Yuan

In addition, CAG exhibits high transferability across different DNN classifier models in black-box attack scenario by introducing random dropout in the process of generating perturbations.

Adversarial Attack

CircConv: A Structured Convolution with Low Complexity

no code implementations28 Feb 2019 Siyu Liao, Zhe Li, Liang Zhao, Qinru Qiu, Yanzhi Wang, Bo Yuan

Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications.

Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank

no code implementations ICML 2017 Liang Zhao, Siyu Liao, Yanzhi Wang, Zhe Li, Jian Tang, Victor Pan, Bo Yuan

Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks.

Cannot find the paper you are looking for? You can Submit a new open access paper.