Exploiting Channel Similarity for Accelerating Deep Convolutional Neural Networks
This work addresses the challenge of model acceleration for deep learning practitioners, offering an incremental improvement over existing pruning techniques.
The paper tackles the problem of accelerating deep convolutional neural networks by proposing a channel pruning method based on channel similarity, which reduces FLOPs by 30% on ResNet-50 while outperforming the baseline model on ImageNet.
To address the limitations of existing magnitude-based pruning algorithms in cases where model weights or activations are of large and similar magnitude, we propose a novel perspective to discover parameter redundancy among channels and accelerate deep CNNs via channel pruning. Precisely, we argue that channels revealing similar feature information have functional overlap and that most channels within each such similarity group can be removed without compromising model's representational power. After deriving an effective metric for evaluating channel similarity through probabilistic modeling, we introduce a pruning algorithm via hierarchical clustering of channels. In particular, the proposed algorithm does not rely on sparsity training techniques or complex data-driven optimization and can be directly applied to pre-trained models. Extensive experiments on benchmark datasets strongly demonstrate the superior acceleration performance of our approach over prior arts. On ImageNet, our pruned ResNet-50 with 30% FLOPs reduced outperforms the baseline model.