Three Dimensional Convolutional Neural Network Pruning with Regularization-Based Method
This work addresses efficiency issues in video analysis for researchers and practitioners, though it is incremental as it builds on existing pruning techniques.
The paper tackles the high computational and storage costs of 3D CNNs by proposing a regularization-based pruning method that assigns parameters based on weight importance and layer redundancy, achieving up to 2x speedup with minimal accuracy loss (e.g., 0.41% for 3DResNet18).
Despite enjoying extensive applications in video analysis, three-dimensional convolutional neural networks (3D CNNs)are restricted by their massive computation and storage consumption. To solve this problem, we propose a threedimensional regularization-based neural network pruning method to assign different regularization parameters to different weight groups based on their importance to the network. Further we analyze the redundancy and computation cost for each layer to determine the different pruning ratios. Experiments show that pruning based on our method can lead to 2x theoretical speedup with only 0.41% accuracy loss for 3DResNet18 and 3.28% accuracy loss for C3D. The proposed method performs favorably against other popular methods for model compression and acceleration.