GeNAS: Neural Architecture Search with Better Generalization

Autor:	Jeong, Joonhyun, Yu, Joonsang, Park, Geondo, Han, Dongyoon, Yoo, YoungJoon
Rok vydání:	2023
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	Neural Architecture Search (NAS) aims to automatically excavate the optimal network architecture with superior test performance. Recent neural architecture search (NAS) approaches rely on validation loss or accuracy to find the superior network for the target data. In this paper, we investigate a new neural architecture search measure for excavating architectures with better generalization. We demonstrate that the flatness of the loss surface can be a promising proxy for predicting the generalization capability of neural network architectures. We evaluate our proposed method on various search spaces, showing similar or even better performance compared to the state-of-the-art NAS methods. Notably, the resultant architecture found by flatness measure generalizes robustly to various shifts in data distribution (e.g. ImageNet-V2,-A,-O), as well as various tasks such as object detection and semantic segmentation. Code is available at https://github.com/clovaai/GeNAS. Comment: Accepted by IJCAI2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2305.08611 Zobrazit plný text záznamu View this record from Arxiv