Convolutional Neural Network Simplification with Progressive Retraining
This work addresses the need for more efficient and interpretable CNN models, particularly for applications in computer vision, though it appears incremental as it builds on existing kernel pruning methods.
The paper tackles the problem of simplifying convolutional neural networks (CNNs) while maintaining effectiveness, introducing methods based on objective and subjective relevance criteria with progressive retraining, resulting in increased effectiveness with considerable model simplification and better results than popular and state-of-the-art methods on four challenging image datasets.
Kernel pruning methods have been proposed to speed up, simplify, and improve explanation of convolutional neural network (CNN) models. However, the effectiveness of a simplified model is often below the original one. In this letter, we present new methods based on objective and subjective relevance criteria for kernel elimination in a layer-by-layer fashion. During the process, a CNN model is retrained only when the current layer is entirely simplified, by adjusting the weights from the next layer to the first one and preserving weights of subsequent layers not involved in the process. We call this strategy \emph{progressive retraining}, differently from kernel pruning methods that usually retrain the entire model after each simplification action -- e.g., the elimination of one or a few kernels. Our subjective relevance criterion exploits the ability of humans in recognizing visual patterns and improves the designer's understanding of the simplification process. The combination of suitable relevance criteria and progressive retraining shows that our methods can increase effectiveness with considerable model simplification. We also demonstrate that our methods can provide better results than two popular ones and another one from the state-of-the-art using four challenging image datasets.