activity
20182026
most citedWeight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap

28 citations · 73 across the 22 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2024

TerDiT: Ternary Diffusion Models with Transformers

Xudong Lu, Aojun Zhou, Ziyi Lin +7

Recent developments in large-scale pre-trained text-to-image diffusion models have significantly improved the generation of high-fidelity images, particularly with the emergence of…

cs.CV2020★ 1 cited

Batch Normalization with Enhanced Linear Transformation

Yuhui Xu, Lingxi Xie, Cihang Xie +5

Batch normalization (BN) is a fundamental unit in modern deep networks, in which a linear transformation module was designed for improving BN's flexibility of fitting complex data…

cs.CV2020★ 28 cited

Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap

Lingxi Xie, Xin Chen, Kaifeng Bi +8

Neural architecture search (NAS) has attracted increasing attentions in both academia and industry. In the early age, researchers mostly applied individual search methods which sam…

cs.CV2020

Latency-Aware Differentiable Neural Architecture Search

Yuhui Xu, Lingxi Xie, Xiaopeng Zhang +4

Differentiable neural architecture search methods became popular in recent years, mainly due to their low search costs and flexibility in designing the search space. However, these…

cs.CV2019★ 13 cited

Trained Rank Pruning for Efficient Deep Neural Networks

Yuhui Xu, Yuxi Li, Shuai Zhang +7

To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attemp…

cs.CV2019

PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search

Yuhui Xu, Lingxi Xie, Xiaopeng Zhang +4

Differentiable architecture search (DARTS) provided a fast solution in finding effective network architectures, but suffered from large memory and computing overheads in jointly tr…