Efficient Fusion of Sparse and Complementary Convolutions

Abstract

We propose a new method to create compact convolutional neural networks (CNNs) by exploiting sparse convolutions. Different from previous works that learn sparsity in models, we directly employ hand-crafted kernels with regular sparse patterns, which result in the computational gain in practice without sophisticated and dedicated software or hardware. The core of our approach is an efficient network module that linearly combines sparse kernels to yield feature representations as strong as those from regular kernels. We integrate this module into various network architectures and demonstrate its effectiveness on three vision tasks, object classification, localization and detection. For object classification and localization, our approach achieves comparable or better performance than several baselines and related works while providing lower computational costs with fewer parameters (on average, a $2-4\times$ reduction of convolutional parameters and computation). For object detection, our approach leads to a VGG-16-based Faster RCNN detector that is 12.4$\times$ smaller and about 3$\times$ faster than the baseline.

arXiv comment10 pages, updated with correct numbers

References in corpus (9)

• Distilling the Knowledge in a Neural Network
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
• Speeding up Convolutional Neural Networks with Low Rank Expansions
• Learning Structured Sparsity in Deep Neural Networks
• Dilated Residual Networks
• Deep Model Compression: Distilling Knowledge from Noisy Teachers
• Cross Modal Distillation for Supervision Transfer