Deep kMeans: ReTraining and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions
[edit]
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:53635372, 2018.
Abstract
The current trend of pushing CNNs deeper with convolutions has created a pressing demand to achieve higher compression gains on CNNs where convolutions dominate the computation and parameter amount (e.g., GoogLeNet, ResNet and Wide ResNet). Further, the high energy consumption of convolutions limits its deployment on mobile devices. To this end, we proposed a simple yet effective scheme for compressing convolutions though applying kmeans clustering on the weights, compression is achieved through weightsharing, by only recording $K$ cluster centers and weight assignment indexes. We then introduced a novel spectrally relaxed $k$means regularization, which tends to make hard assignments of convolutional layer weights to $K$ learned cluster centers during retraining. We additionally propose an improved set of metrics to estimate energy consumption of CNN hardware implementations, whose estimation results are verified to be consistent with previously proposed energy estimation tool extrapolated from actual hardware measurements. We finally evaluated Deep $k$Means across several CNN models in terms of both compression ratio and energy consumption reduction, observing promising results without incurring accuracy loss. The code is available at https://github.com/Sandbox3aster/DeepKMeans
Related Material


