Learning Versatile Convolution Filters for Efficient Visual Recognition

Abstract

This paper introduces versatile filters to construct efficient convolutional neural networks that are widely used in various visual recognition tasks. Considering the demands of efficient deep learning techniques running on cost-effective hardware, a number of methods have been developed to learn compact neural networks. Most of these works aim to slim down filters in different ways, \eg,~investigating small, sparse or quantized filters. In contrast, we treat filters from an additive perspective. A series of secondary filters can be derived from a primary filter with the help of binary masks. These secondary filters all inherit in the primary filter without occupying more storage, but once been unfolded in computation they could significantly enhance the capability of the filter by integrating information extracted from different receptive fields. Besides spatial versatile filters, we additionally investigate versatile filters from the channel perspective. Binary masks can be further customized for different primary filters under orthogonal constraints. We conduct theoretical analysis on network complexity and an efficient convolution scheme is introduced. Experimental results on benchmark datasets and neural networks demonstrate that our versatile filters are able to achieve comparable accuracy as that of original filters, but require less memory and computation cost.

Accepted by TPAMI. Extended version of NeurIPS 2018 paper

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Neural Architecture Search with Reinforcement Learning
• FitNets: Hints for Thin Deep Nets
• Speeding up Convolutional Neural Networks with Low Rank Expansions
• Learning Structured Sparsity in Deep Neural Networks
• Channel Pruning for Accelerating Very Deep Neural Networks
• Slimmable Neural Networks
• Towards Optimal Structured CNN Pruning via Generative Adversarial Learning
• FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
• Learning Implicitly Recurrent CNNs Through Parameter Sharing