SCSP: Spectral Clustering Filter Pruning with Soft Self-adaption Manners
This work addresses the deployment of CNNs on edge devices with limited resources, presenting an incremental improvement in model compression techniques.
The paper tackles the problem of high computational cost in deep convolutional neural networks (CNNs) by proposing SCSP, a novel filter pruning method using spectral clustering and soft self-adaption, achieving model compression while maintaining considerable performance.
Deep Convolutional Neural Networks (CNN) has achieved significant success in computer vision field. However, the high computational cost of the deep complex models prevents the deployment on edge devices with limited memory and computational resource. In this paper, we proposed a novel filter pruning for convolutional neural networks compression, namely spectral clustering filter pruning with soft self-adaption manners (SCSP). We first apply spectral clustering on filters layer by layer to explore their intrinsic connections and only count on efficient groups. By self-adaption manners, the pruning operations can be done in few epochs to let the network gradually choose meaningful groups. According to this strategy, we not only achieve model compression while keeping considerable performance, but also find a novel angle to interpret the model compression process.