Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration

Abstract

The training of deep neural networks (DNNs) always requires intensive resources for both computation and data storage. Thus, DNNs cannot be efficiently applied to mobile phones and embedded devices, which severely limits their applicability in industrial applications. To address this issue, we propose a novel encoding scheme using {-1, +1} to decompose quantized neural networks (QNNs) into multi-branch binary networks, which can be efficiently implemented by bitwise operations (i.e., xnor and bitcount) to achieve model compression, computational acceleration, and resource saving. By using our method, users can achieve different encoding precisions arbitrarily according to their requirements and hardware resources. The proposed mechanism is highly suitable for the use of FPGA and ASIC in terms of data storage and computation, which provides a feasible idea for smart chips. We validate the effectiveness of our method on large-scale image classification (e.g., ImageNet), object detection, and semantic segmentation tasks. In particular, our method with low-bit encoding can still achieve almost the same performance as its high-bit counterparts.

arXiv commentarXiv admin note: substantial text overlap with arXiv:1905.13389

References in corpus (23)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
• Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• DARTS: Differentiable Architecture Search
• Binarized Neural Networks
• Ternary Weight Networks
• Fixed Point Quantization of Deep Convolutional Networks
• Convolutional Neural Networks using Logarithmic Data Representation
• Mixed Precision DNNs: All you need is a good parametrization
• From Hashing to CNNs: Training BinaryWeight Networks via Hashing
• Robust Quantization: One Model to Rule Them All
• Defensive Quantization: When Efficiency Meets Robustness
• Rethinking Differentiable Search for Mixed-Precision Neural Networks
• MWQ: Multiscale Wavelet Quantized Neural Networks
• Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization
• Dataflow-based Joint Quantization of Weights and Activations for Deep Neural Networks
• One Model for All Quantization: A Quantized Network Supporting Hot-Swap Bit-Width Adjustment