# Compact Deep Convolutional Neural Networks With Coarse Pruning

arXiv: https://arxiv.org/abs/1610.09639 · HTML: https://mlsanity.com/paper/1610.09639/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2016.

## Built on by (most cited first, 3 of 3)

- [A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification](https://mlsanity.com/paper/2205.07877/) (2022)
- [Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report](https://mlsanity.com/paper/2211.05910/) (2022)
- [Pruning Very Deep Neural Network Channels for Efficient Inference](https://mlsanity.com/paper/2211.08339/) (2022)

## Abstract (arXiv)

The learning capability of a neural network improves with increasing depth at higher computational costs. Wider layers with dense kernel connectivity patterns furhter increase this cost and may hinder real-time inference. We propose feature map and kernel level pruning for reducing the computational complexity of a deep convolutional neural network. Pruning feature maps reduces the width of a layer and hence does not need any sparse representation. Further, kernel pruning converts the dense connectivity pattern into a sparse one. Due to coarse nature, these pruning granularities can be exploited by GPUs and VLSI based implementations. We propose a simple and generic strategy to choose the least adversarial pruning masks for both granularities. The pruned networks are retrained which compensates the loss in accuracy. We obtain the best pruning ratios when we prune a network with both granularities. Experiments with the CIFAR-10 dataset show that more than 85% sparsity can be induced in the convolution layers with less than 1% increase in the missclassification rate of the baseline network.