MWQ: Multiscale Wavelet Quantized Neural Networks

Abstract

Model quantization can reduce the model size and computational latency, it has become an essential technique for the deployment of deep neural networks on resourceconstrained hardware (e.g., mobile phones and embedded devices). The existing quantization methods mainly consider the numerical elements of the weights and activation values, ignoring the relationship between elements. The decline of representation ability and information loss usually lead to the performance degradation. Inspired by the characteristics of images in the frequency domain, we propose a novel multiscale wavelet quantization (MWQ) method. This method decomposes original data into multiscale frequency components by wavelet transform, and then quantizes the components of different scales, respectively. It exploits the multiscale frequency and spatial information to alleviate the information loss caused by quantization in the spatial domain. Because of the flexibility of MWQ, we demonstrate three applications (e.g., model compression, quantized network optimization, and information enhancement) on the ImageNet and COCO datasets. Experimental results show that our method has stronger representation ability and can play an effective role in quantized neural networks.

References in corpus (16)

• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
• A Survey of Model Compression and Acceleration for Deep Neural Networks
• Ternary Weight Networks
• Trained Ternary Quantization
• PACT: Parameterized Clipping Activation for Quantized Neural Networks
• Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights
• Convolutional Neural Networks using Logarithmic Data Representation
• Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search
• ShiftCNN: Generalized Low-Precision Architecture for Inference of Convolutional Neural Networks
• Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference
• Multi-wavelet residual dense convolutional neural network for image denoising
• AdaBits: Neural Network Quantization with Adaptive Bit-Widths
• Rethinking Differentiable Search for Mixed-Precision Neural Networks
• WaveSNet: Wavelet Integrated Deep Networks for Image Segmentation
• Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization

Cited by in corpus (2)

• One Model for All Quantization: A Quantized Network Supporting Hot-Swap Bit-Width Adjustment
• Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration