ScarletNAS: Bridging the Gap Between Scalability and Fairness in Neural Architecture Search

By Xiangxiang Chu, Bo Zhang, Jixiang Li, Qingyuan Li, Ruijun Xu. 2019

27 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Xiaodan Liang
2. Liang Lin
3. Xiaojun Chang
4. Fei Wang
5. Dacheng Tao
6. Yi Yang
7. Changlin Li
8. Zhenguo Li

Citations in the corpus

• GreedyNAS: Towards Fast One-Shot NAS With Greedy Supernet (2020, methodology): “Current methods [16, 11, 4, 3] hold the assumption that the supernet should estimate the (relative) performance accurately for all paths, and thus all paths are treated equally and trained simultaneously.”
• StacNAS: Towards Stable and Consistent Differentiable Neural Architecture Search (2019, result): “This result beats the current state-of-the-artEfficientNetB0 (Tan & Le (2019)) and SCARLET-C Chu et al. (2019a) at the similar model size.”
• Block-Wisely Supervised Neural Architecture Search With Knowledge Distillation (2019, methodology): “We keep our first search space similar with most of the recent works [29, 30, 12, 13] to facilitate fair comparison in Section 4.”