GhostNet: More Features from Cheap Operations

Deploying convolutional neural networks (CNNs) on embedded devices is difficult due to the limited memory and computation resources. The redundancy in feature maps is an important characteristic of those successful CNNs, but has rarely been investigated in neural architecture design... (read more)

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification ImageNet GhostNet Top 1 Accuracy 75.7% # 122
Top 5 Accuracy 92.7% # 83
Number of params 7.3M # 59

Methods used in the Paper