Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution

10 Apr 2019Yunpeng ChenHaoqi FanBing XuZhicheng YanYannis KalantidisMarcus RohrbachShuicheng YanJiashi Feng

In natural images, information is conveyed at different frequencies where higher frequencies are usually encoded with fine details and lower frequencies are usually encoded with global structures. Similarly, the output feature maps of a convolution layer can also be seen as a mixture of information at different frequencies... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Image Classification ImageNet Oct-ResNet-152 (SE) Top 1 Accuracy 82.9% # 14
Image Classification ImageNet Oct-ResNet-152 (SE) Top 5 Accuracy 96.3% # 13
Image Classification ImageNet Oct-ResNet-152 (SE) Number of params 67M # 1