Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution
This paper proposes a novel module called middle spectrum grouped convolution (MSGC) for efficient deep convolutional neural networks (DCNNs) with the mechanism of grouped convolution. It explores the broad "middle spectrum" area between channel pruning and conventional grouped convolution. Compared with channel pruning, MSGC can retain most of the information from the input feature maps due to the group mechanism; compared with grouped convolution, MSGC benefits from the learnability, the core of channel pruning, for constructing its group topology, leading to better channel division. The middle spectrum area is unfolded along four dimensions: group-wise, layer-wise, sample-wise, and attention-wise, making it possible to reveal more powerful and interpretable structures. As a result, the proposed module acts as a booster that can reduce the computational cost of the host backbones for general image recognition with even improved predictive accuracy. For example, in the experiments on ImageNet dataset for image classification, MSGC can reduce the multiply-accumulates (MACs) of ResNet-18 and ResNet-50 by half but still increase the Top-1 accuracy by more than 1%. With 35% reduction of MACs, MSGC can also increase the Top-1 accuracy of the MobileNetV2 backbone. Results on MS COCO dataset for object detection show similar observations. Our code and trained models are available at https://github.com/hellozhuo/msgc.
Code (1)
Tasks
image-classificationImage Classificationobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
An Enhanced Scheme for Reducing the Complexity of Pointwise Convolutions in CNNs for Image Classification Based on Interleaved Grouped Filters without Divisibility Constraints
In image classification with Deep Convolutional Neural Networks (DCNNs), the number of parameters in pointwise convolutions rapidly grows due to the multiplication of the number of filters by the number of input channels…
image-classificationImage ClassificationBeyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering
Graph convolutional networks are becoming indispensable for deep learning from graph-structured data. Most of the existing graph convolutional networks share two big shortcomings. First, they are essentially low-pass fil…
IoT Malware Detection Architecture using a Novel Channel Boosted and Squeezed CNN
Interaction between devices, people, and the Internet has given birth to a new digital communication model, the Internet of Things (IoT). The seamless network of these smart devices is the core of this IoT model. However…
Malware DetectionRobust Boosting Forests with Richer Deep Feature Hierarchy
We propose a robust variant of boosting forest to the various adversarial defense methods, and apply it to enhance the robustness of the deep neural network. We retain the deep network architecture, weights, and middle l…
Adversarial DefenseFace ModelGroSS: Group-Size Series Decomposition for Grouped Architecture Search
We present a novel approach which is able to explore the configuration of grouped convolutions within neural networks. Group-size Series (GroSS) decomposition is a mathematical formulation of tensor factorisation into a …