Knowledge Distillation By Sparse Representation Matching

Abstract

Knowledge Distillation refers to a class of methods that transfers the knowledge from a teacher network to a student network. In this paper, we propose Sparse Representation Matching (SRM), a method to transfer intermediate knowledge obtained from one Convolutional Neural Network (CNN) to another by utilizing sparse representation learning. SRM first extracts sparse representations of the hidden features of the teacher CNN, which are then used to generate both pixel-level and image-level labels for training intermediate feature maps of the student network. We formulate SRM as a neural processing block, which can be efficiently optimized using stochastic gradient descent and integrated into any CNN in a plug-and-play manner. Our experiments demonstrate that SRM is robust to architectural differences between the teacher and student networks, and outperforms other KD techniques across several datasets.

9 pages

References in corpus (8)

• Distilling the Knowledge in a Neural Network
• Neural Architecture Search with Reinforcement Learning
• Striving for Simplicity: The All Convolutional Net
• FitNets: Hints for Thin Deep Nets
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• Speeding up Convolutional Neural Networks with Low Rank Expansions
• Data-Free Knowledge Distillation for Deep Neural Networks
• Multilinear Compressive Learning with Prior Knowledge