Joint Pruning & Quantization for Extremely Sparse Neural Networks
We investigate pruning and quantization for deep neural networks. Our goal is to achieve extremely high sparsity for quantized networks to enable implementation on low cost and low power accelerator hardware. In a practical scenario, there are particularly many applications for dense prediction tasks, hence we choose stereo depth estimation as target. We propose a two stage pruning and quantization pipeline and introduce a Taylor Score alongside a new fine-tuning mode to achieve extreme sparsity without sacrificing performance. Our evaluation does not only show that pruning and quantization should be investigated jointly, but also shows that almost 99% of memory demand can be cut while hardware costs can be reduced up to 99.9%. In addition, to compare with other works, we demonstrate that our pruning stage alone beats the state-of-the-art when applied to ResNet on CIFAR10 and ImageNet.
Code (0)
등록된 구현이 없습니다.
Tasks
Depth EstimationQuantizationStereo Depth EstimationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Neural Network Compression using Binarization and Few Full-Precision Weights
Quantization and pruning are two effective Deep Neural Networks model compression methods. In this paper, we propose Automatic Prune Binarization (APB), a novel compression technique combining quantization with pruning. …
BinarizationCPUModel CompressionNeural Network Compression+1Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression
Structured pruning and quantization are fundamental techniques used to reduce the size of deep neural networks (DNNs) and typically are applied independently. Applying these techniques jointly via co-optimization has the…
Efficient Neural NetworkQuantizationDifferentiable Joint Pruning and Quantization for Hardware Efficiency
We present a differentiable joint pruning and quantization (DJPQ) scheme. We frame neural network compression as a joint gradient-based optimization problem, trading off between model pruning and quantization automatical…
Neural Network CompressionQuantizationAWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent
To address the enormous size of Large Language Models (LLMs), model compression methods, such as quantization and pruning, are often deployed, especially on edge devices. In this work, we focus on layer-wise post-trainin…
Model CompressionQuantizationAutomated Model Compression by Jointly Applied Pruning and Quantization
In the traditional deep compression framework, iteratively performing network pruning and quantization can reduce the model size and computation cost to meet the deployment requirements. However, such a step-wise applica…
AutoMLModel CompressionNetwork Pruningobject-detection+2