Search Results - "Xue, Fanghui"

RARTS: An Efficient First-Order Relaxed Architecture Search Method by Xue, Fanghui, Qi, Yingyong, Xin, Jack

“…Differentiable architecture search (DARTS) is an effective method for data-driven neural network design based on solving a bilevel optimization problem…”
Get full text

Relaxation and Optimization for Automated Learning of Neural Network Architectures by Xue, Fanghui

“…Differentiable architecture search (DARTS) is an effective method for data-driven neural network design based on bilevel optimization. Despite its success in…”
Get full text

Network Compression via Cooperative Architecture Search and Distillation by Xue, Fanghui, Xin, Jack

“…Neural Architecture Search (NAS) and its variants are competitive in many computer vision tasks lately. In this paper, we develop a Cooperative Architecture…”
Get full text

RARTS: An Efficient First-Order Relaxed Architecture Search Method by Xue, Fanghui, Qi, Yingyong, Xin, Jack

“…Differentiable architecture search (DARTS) is an effective method for data-driven neural network design based on solving a bilevel optimization problem…”
Get full text

Learning Sparse Neural Networks via $\ell_0$ and T$\ell_1$ by a Relaxed Variable Splitting Method with Application to Multi-scale Curve Classification by Xue, Fanghui, Xin, Jack

“…We study sparsification of convolutional neural networks (CNN) by a relaxed variable splitting method of $\ell_0$ and transformed-$\ell_1$ (T$\ell_1$)…”
Get full text

A Proximal Algorithm for Network Slimming by Bui, Kevin, Xue, Fanghui, Park, Fredrick, Qi, Yingyong, Xin, Jack

“…As a popular channel pruning method for convolutional neural networks (CNNs), network slimming (NS) has a three-stage process: (1) it trains a CNN with…”
Get full text

AFIDAF: Alternating Fourier and Image Domain Adaptive Filters as an Efficient Alternative to Attention in ViTs by Zheng, Yunling, Xu, Zeyi, Xue, Fanghui, Yang, Biao, Lyu, Jiancheng, Zhang, Shuai, Qi, Yingyong, Xin, Jack

“…We propose and demonstrate an alternating Fourier and image domain filtering approach for feature extraction as an efficient alternative to build a vision…”
Get full text

Searching Intrinsic Dimensions of Vision Transformers by Xue, Fanghui, Yang, Biao, Qi, Yingyong, Xin, Jack

“…It has been shown by many researchers that transformers perform as well as convolutional neural networks in many computer vision tasks. Meanwhile, the large…”
Get full text

Short Paper: A Multistage Backward Differentiable Method for Constructing Light Convolutional Neural Networks by Xue, Fanghui, Xin, Jack, Lyu, Jiancheng, Zhang, Shuai, Qi, Yingyong

“…We propose a multistage differentiable method to select convolutional channels and construct light neural networks from a heavy network for inference on a…”
Get full text