Robust Quantization: One Model to Rule Them All
arXiv:2002.07686
Abstract
Neural network quantization methods often involve simulating the quantization process during training, making the trained model highly dependent on the target bit-width and precise way quantization is performed. Robust quantization offers an alternative approach with improved tolerance to different classes of data-types and quantization policies. It opens up new exciting applications where the quantization process is not static and can vary to meet different circumstances and implementations. To address this issue, we propose a method that provides intrinsic robustness to the model against a broad range of quantization processes. Our method is motivated by theoretical arguments and enables us to store a single generic model capable of operating at various bit-widths and quantization policies. We validate our method's effectiveness on different ImageNet models.
References in corpus (13)
- Deep Residual Learning for Image Recognition
- DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
- Quantizing deep convolutional networks for efficient inference: A whitepaper
- PACT: Parameterized Clipping Activation for Quantized Neural Networks
- Learned Step Size Quantization
- Improving Neural Network Quantization without Retraining using Outlier Channel Splitting
- Post-training 4-bit quantization of convolution networks for rapid-deployment
- Neural Network Distiller: A Python Package For DNN Compression Research
- NICE: Noise Injection and Clamping Estimation for Neural Network Quantization
- Quantization for Rapid Deployment of Deep Neural Networks
- Fighting Quantization Bias With Bias
- SinReQ: Generalized Sinusoidal Regularization for Low-Bitwidth Deep Quantized Training
- GDRQ: Group-based Distribution Reshaping for Quantization
Cited by in corpus (8)
- Pareto-Optimal Quantized ResNet Is Mostly 4-bit
- Degree-Quant: Quantization-Aware Training for Graph Neural Networks
- One Model for All Quantization: A Quantized Network Supporting Hot-Swap Bit-Width Adjustment
- Post-Training BatchNorm Recalibration
- Non-Blocking Simultaneous Multithreading: Embracing the Resiliency of Deep Neural Networks
- Anchor-based Plain Net for Mobile Image Super-Resolution
- Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration
- Quantization Aware Training, ERNIE and Kurtosis Regularizer: a short empirical study