Functionality-Oriented Convolutional Filter Pruning
This work addresses computational inefficiency in CNNs for applications like image processing, but it is incremental as it builds on existing filter pruning techniques by adding interpretability.
The paper tackled the problem of computational redundancy in Convolutional Neural Networks (CNNs) by proposing a functionality-oriented filter pruning method that considers qualitative filter interpretations, resulting in outstanding computation cost optimization over previous methods.
The sophisticated structure of Convolutional Neural Network (CNN) allows for outstanding performance, but at the cost of intensive computation. As significant redundancies inevitably present in such a structure, many works have been proposed to prune the convolutional filters for computation cost reduction. Although extremely effective, most works are based only on quantitative characteristics of the convolutional filters, and highly overlook the qualitative interpretation of individual filter's specific functionality. In this work, we interpreted the functionality and redundancy of the convolutional filters from different perspectives, and proposed a functionality-oriented filter pruning method. With extensive experiment results, we proved the convolutional filters' qualitative significance regardless of magnitude, demonstrated significant neural network redundancy due to repetitive filter functions, and analyzed the filter functionality defection under inappropriate retraining process. Such an interpretable pruning approach not only offers outstanding computation cost optimization over previous filter pruning methods, but also interprets filter pruning process.