Demystifying Neural Network Filter Pruning
This addresses the issue of inefficient pruning for researchers and practitioners in deep learning, though it is incremental as it builds on existing filter pruning approaches.
The paper tackled the problem of filter pruning in CNNs by analyzing filter functionality, finding that conventional magnitude-based methods fail to remove redundant filters and require retraining for compensation. It proposed a functionality-oriented method that prunes CNNs without significant accuracy drop and eliminates the need for retraining.
Based on filter magnitude ranking (e.g. L1 norm), conventional filter pruning methods for Convolutional Neural Networks (CNNs) have been proved with great effectiveness in computation load reduction. Although effective, these methods are rarely analyzed in a perspective of filter functionality. In this work, we explore the filter pruning and the retraining through qualitative filter functionality interpretation. We find that the filter magnitude based method fails to eliminate the filters with repetitive functionality. And the retraining phase is actually used to reconstruct the remained filters for functionality compensation for the wrongly-pruned critical filters. With a proposed functionality-oriented pruning method, we further testify that, by precisely addressing the filter functionality redundancy, a CNN can be pruned without considerable accuracy drop, and the retraining phase is unnecessary.