Aggregated Residual Transformations for Deep Neural Networks

CVPR 2017 Saining XieRoss GirshickPiotr DollárZhuowen TuKaiming He

We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Image Classification ImageNet ResNeXt-101 64x4 Top 1 Accuracy 80.9% # 43
Image Classification ImageNet ResNeXt-101 64x4 Top 5 Accuracy 95.6% # 27
Image Classification ImageNet ResNeXt-101 64x4 Number of params 83.6M # 1