Filter Grafting for Deep Neural Networks

Abstract

This paper proposes a new learning paradigm called filter grafting, which aims to improve the representation capability of Deep Neural Networks (DNNs). The motivation is that DNNs have unimportant (invalid) filters (e.g., l1 norm close to 0). These filters limit the potential of DNNs since they are identified as having little effect on the network. While filter pruning removes these invalid filters for efficiency consideration, filter grafting re-activates them from an accuracy boosting perspective. The activation is processed by grafting external information (weights) into invalid filters. To better perform the grafting process, we develop an entropy-based criterion to measure the information of filters and an adaptive weighting strategy for balancing the grafted information among networks. After the grafting operation, the network has very few invalid filters compared with its untouched state, enpowering the model with more representation capacity. We also perform extensive experiments on the classification and recognition tasks to show the superiority of our method. For example, the grafted MobileNetV2 outperforms the non-grafted MobileNetV2 by about 7 percent on CIFAR-100 dataset. Code is available at https://github.com/fxmeng/filter-grafting.git.

Accepted by CVPR2020

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• Opening the Black Box of Deep Neural Networks via Information
• Pruning Filters for Efficient ConvNets
• Text Understanding from Scratch
• Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
• On weight initialization in deep neural networks
• Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers
• Omni-Scale Feature Learning for Person Re-Identification
• Exploring Linear Relationship in Feature Map Subspace for ConvNets Compression
• SCSP: Spectral Clustering Filter Pruning with Soft Self-adaption Manners

Cited by in corpus (4)

• Compacting Deep Neural Networks for Internet of Things: Methods and Applications
• One Person, One Model, One World: Learning Continual User Representation without Forgetting
• Vehicle Re-Identification Based on Complementary Features
• Ferrograph image classification