GeNAS: Neural Architecture Search with Better Generalization
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.
Code (1)
Tasks
Neural Architecture Searchobject-detectionObject DetectionSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
AdvantageNAS: Efficient Neural Architecture Search with Credit Assignment
Neural architecture search (NAS) is an approach for automatically designing a neural network architecture without human effort or expert knowledge. However, the high computational cost of NAS limits its use in commercial…
Neural Architecture SearchGenetic Neural Architecture Search for automatic assessment of human sperm images
Male infertility is a disease which affects approximately 7% of men. Sperm morphology analysis (SMA) is one of the main diagnosis methods for this problem. Manual SMA is an inexact, subjective, non-reproducible, and hard…
Anomaly DetectionNeural Architecture SearchEvaluation of the Penetration Process of Fluorescent Collagenase Nanocapsules in a 3D Collagen Gel
One of the major limitations of nanomedicine is the scarce penetration of nanoparticles in tumoral tissues. These constrains have been tried to be solved by different strategies, such as the employ of polyethyleneglycol …
Collagenase Nanocapsules: An Approach to Fibrosis Treatment
Fibrosis is a common lesion in different pathologic diseases and is defined by the excessive accumulation of collagen. Different approaches have been used to treat different conditions characterized by fibrosis. FDA and …
Collaborative learning of images and geometrics for predicting isocitrate dehydrogenase status of glioma
The isocitrate dehydrogenase (IDH) gene mutation status is an important biomarker for glioma patients. The gold standard of IDH mutation detection requires tumour tissue obtained via invasive approaches and is usually ex…