-
FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary
We present a novel method of compression of deep Convolutional Neural Ne...
read it
-
Optimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracy
Deep convolution neural network has achieved great success in many artif...
read it
-
Kernel Quantization for Efficient Network Compression
This paper presents a novel network compression framework Kernel Quantiz...
read it
-
Compressing Deep Convolutional Neural Networks by Stacking Low-dimensional Binary Convolution Filters
Deep Convolutional Neural Networks (CNN) have been successfully applied ...
read it
-
Ternary MobileNets via Per-Layer Hybrid Filter Banks
MobileNets family of computer vision neural networks have fueled tremend...
read it
-
Leveraging Filter Correlations for Deep Model Compression
We present a filter correlation based model compression approach for dee...
read it
-
A Main/Subsidiary Network Framework for Simplifying Binary Neural Network
To reduce memory footprint and run-time latency, techniques such as neur...
read it
Cross-filter compression for CNN inference acceleration
Convolution neural network demonstrates great capability for multiple tasks, such as image classification and many others. However, much resource is required to train a network. Hence much effort has been made to accelerate neural network by reducing precision of weights, activation, and gradient. However, these filter-wise quantification methods exist a natural upper limit, caused by the size of the kernel. Meanwhile, with the popularity of small kernel, the natural limit further decrease. To address this issue, we propose a new cross-filter compression method that can provide ∼32× memory savings and 122× speed up in convolution operations. In our method, all convolution filters are quantized to given bits and spatially adjacent filters share the same scaling factor. Our compression method, based on Binary-Weight and XNOR-Net separately, is evaluated on CIFAR-10 and ImageNet dataset with widely used network structures, such as ResNet and VGG, and witness tolerable accuracy loss compared to state-of-the-art quantification methods.
READ FULL TEXT
Comments
There are no comments yet.