Learning Transferable Architectures for Scalable Image Recognition

CVPR 2018 Barret ZophVijay VasudevanJonathon ShlensQuoc V. Le

Developing neural network image classification models often requires significant architecture engineering. In this paper, we study a method to learn the model architectures directly on the dataset of interest... (read more)

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification ImageNet NASNET-A(6) Top 1 Accuracy 82.7% # 35
Top 5 Accuracy 96.2% # 25
Number of params 88.9M # 11

Methods used in the Paper