Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks
arXiv:1910.09455 · doi:10.54364/AAIML.2023.1197
Abstract
Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, which results in high inference latency. Recently, depth-wise separable convolution has been proposed for image recognition tasks on computationally limited platforms such as robotics and self-driving cars. Though it is much faster than its counterpart, regular convolution, accuracy is sacrificed. In this paper, we propose a novel decomposition approach based on SVD, namely depth-wise decomposition, for expanding regular convolutions into depthwise separable convolutions while maintaining high accuracy. We show our approach can be further generalized to the multi-channel and multi-layer cases, based on Generalized Singular Value Decomposition (GSVD) [59]. We conduct thorough experiments with the latest ShuffleNet V2 model [47] on both random synthesized dataset and a large-scale image recognition dataset: ImageNet [10]. Our approach outperforms channel decomposition [73] on all datasets. More importantly, our approach improves the Top-1 accuracy of ShuffleNet V2 by ~2%.
References in corpus (24)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
- Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices
- cuDNN: Efficient Primitives for Deep Learning
- Compressing Deep Convolutional Networks using Vector Quantization
- A Survey of Model Compression and Acceleration for Deep Neural Networks
- Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures
- Speeding up Convolutional Neural Networks with Low Rank Expansions
- Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
- Fast Training of Convolutional Networks through FFTs
- Fast Convolutional Nets With fbfft: A GPU Performance Evaluation
- Learning the Number of Neurons in Deep Networks
- Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications
- Network Decoupling: From Regular to Depthwise Separable Convolutions
- Diversity Networks: Neural Network Compression Using Determinantal Point Processes
- Bounding Box Regression with Uncertainty for Accurate Object Detection
- Compact Deep Convolutional Neural Networks With Coarse Pruning
- Vehicle Traffic Driven Camera Placement for Better Metropolis Security Surveillance
- MoBiNet: A Mobile Binary Network for Image Classification
- Single Image Super-resolution via a Lightweight Residual Convolutional Neural Network
- LIT: Block-wise Intermediate Representation Training for Model Compression
- Prediction-Tracking-Segmentation