Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
International Conference on Computer Vision, pp. 3435-3444, 2019.
We address the problem of reducing spatial redundancy that widely exists in vanilla Convolutional Neural Networks models, and propose a novel Octave Convolution operation to store and process low- and high-frequency features separately to improve the model efficiency
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. In this work, ...More
PPT (Upload PPT)