activity
20182024
most citedPi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift

2 citations · 2 across the 3 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2024

DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions

Guangrun Wang, Changlin Li, Liuchun Yuan +5

Neural Architecture Search (NAS), aiming at automatically designing neural architectures by machines, has been considered a key step toward automatic machine learning. One notable…

cs.CV20212 cited

Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift

Jiefeng Peng, Jiqi Zhang, Changlin Li +3

Recently proposed neural architecture search (NAS) methods co-train billions of architectures in a supernet and estimate their potential accuracy using the network weights detached…

cs.CV2021

BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search

Changlin Li, Tao Tang, Guangrun Wang +4

A myriad of recent breakthroughs in hand-crafted neural architectures for visual recognition have highlighted the urgent need to explore hybrid architectures consisting of diversif…

cs.CV2019

Blockwisely Supervised Neural Architecture Search with Knowledge Distillation

Changlin Li, Jiefeng Peng, Liuchun Yuan +4

Neural Architecture Search (NAS), aiming at automatically designing network architectures by machines, is hoped and expected to bring about a new revolution in machine learning. De…

cs.CV2018

Learning Deep Representations for Semantic Image Parsing: a Comprehensive Overview

Lili Huang, Jiefeng Peng, Ruimao Zhang +2

Semantic image parsing, which refers to the process of decomposing images into semantic regions and constructing the structure representation of the input, has recently aroused wid…

cs.CV2018

Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches

Guangrun Wang, Jiefeng Peng, Ping Luo +2

As an indispensable component, Batch Normalization (BN) has successfully improved the training of deep neural networks (DNNs) with mini-batches, by normalizing the distribution of…