133 citations · 210 across the 4 of their papers we have counts for
9 papers
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…
GOLD-NAS: Gradual, One-Level, Differentiable
Kaifeng Bi, Lingxi Xie, Xin Chen +2
There has been a large literature of neural architecture search, but most existing work made use of heuristic rules that largely constrained the search flexibility. In this paper,…
Circumventing Outliers of AutoAugment with Knowledge Distillation
Longhui Wei, An Xiao, Lingxi Xie +3
AutoAugment has been a powerful algorithm that improves the accuracy of many vision tasks, yet it is sensitive to the operator space as well as hyper-parameters, and an improper se…
Progressive DARTS: Bridging the Optimization Gap for NAS in the Wild
Xin Chen, Lingxi Xie, Jun Wu +1
With the rapid development of neural architecture search (NAS), researchers found powerful network architectures for a wide range of vision tasks. However, it remains unclear if th…
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…
Stabilizing DARTS with Amended Gradient Estimation on Architectural Parameters
Kaifeng Bi, Changping Hu, Lingxi Xie +3
DARTS is a popular algorithm for neural architecture search (NAS). Despite its great advantage in search efficiency, DARTS often suffers weak stability, which reflects in the large…