Filter Pruning via Filters Similarity in Consecutive Layers
This addresses the need for efficient CNN deployment in resource-constrained environments, but it is incremental as it builds on existing filter pruning techniques by adding cross-layer considerations.
The paper tackles the problem of compressing and accelerating Convolutional Neural Networks (CNNs) by proposing a filter pruning method that leverages filters similarity in consecutive layers, resulting in remarkable improvements in accuracy, FLOPs, and parameter reduction on benchmark models and datasets.
Filter pruning is widely adopted to compress and accelerate the Convolutional Neural Networks (CNNs), but most previous works ignore the relationship between filters and channels in different layers. Processing each layer independently fails to utilize the collaborative relationship across layers. In this paper, we intuitively propose a novel pruning method by explicitly leveraging the Filters Similarity in Consecutive Layers (FSCL). FSCL compresses models by pruning filters whose corresponding features are more worthless in the model. The extensive experiments demonstrate the effectiveness of FSCL, and it yields remarkable improvement over state-of-the-art on accuracy, FLOPs and parameter reduction on several benchmark models and datasets.