activity
20182021
most citedNSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search

15 citations · 23 across the 5 of their papers we have counts for

collaborators

9 papers

cs.LG2021

Accelerating Multi-Objective Neural Architecture Search by Random-Weight Evaluation

Shengran Hu, Ran Cheng, Cheng He +3

For the goal of automated design of high-performance deep convolutional neural networks (CNNs), Neural Architecture Search (NAS) methodology is becoming increasingly important for…

cs.CV20212 cited

FaPN: Feature-aligned Pyramid Network for Dense Image Prediction

Shihua Huang, Zhichao Lu, Ran Cheng +1

Recent advancements in deep neural networks have made remarkable leap-forwards in dense image prediction. However, the issue of feature alignment remains as neglected by most exist…

cs.CV2021

The surprising impact of mask-head architecture on novel class segmentation

Vighnesh Birodkar, Zhichao Lu, Siyang Li +2

Instance segmentation models today are very accurate when trained on large annotated datasets, but collecting mask annotations at scale is prohibitively expensive. We address the p…

cs.CV20201 cited

Multi-objective Neural Architecture Search with Almost No Training

Shengran Hu, Ran Cheng, Cheng He +1

In the recent past, neural architecture search (NAS) has attracted increasing attention from both academia and industries. Despite the steady stream of impressive empirical results…

cs.CV202015 cited

NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search

Zhichao Lu, Kalyanmoy Deb, Erik Goodman +2

In this paper, we propose an efficient NAS algorithm for generating task-specific models that are competitive under multiple competing objectives. It comprises of two surrogates, o…

cs.CV2020

Neural Architecture Transfer

Zhichao Lu, Gautam Sreekumar, Erik Goodman +3

Neural architecture search (NAS) has emerged as a promising avenue for automatically designing task-specific neural networks. Existing NAS approaches require one complete search fo…