Network Quantization with Element-wise Gradient Scaling

• URL: http://arxiv.org/abs/2104.00903v1
• Date: Fri, 2 Apr 2021 06:34:53 GMT
• Title: Network Quantization with Element-wise Gradient Scaling
• Authors: Junghyup Lee, Dohyung Kim, Bumsub Ham
• Abstract summary: Network quantization aims at reducing bit-widths of weights and/or activations. Most methods use the straight-through estimator (STE) to train quantized networks. We propose an element-wise gradient scaling (EWGS) to train a quantized network better than the STE.
• Score: 30.06895253269116
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Network quantization aims at reducing bit-widths of weights and/or activations, particularly important for implementing deep neural networks with limited hardware resources. Most methods use the straight-through estimator (STE) to train quantized networks, which avoids a zero-gradient problem by replacing a derivative of a discretizer (i.e., a round function) with that of an identity function. Although quantized networks exploiting the STE have shown decent performance, the STE is sub-optimal in that it simply propagates the same gradient without considering discretization errors between inputs and outputs of the discretizer. In this paper, we propose an element-wise gradient scaling (EWGS), a simple yet effective alternative to the STE, training a quantized network better than the STE in terms of stability and accuracy. Given a gradient of the discretizer output, EWGS adaptively scales up or down each gradient element, and uses the scaled gradient as the one for the discretizer input to train quantized networks via backpropagation. The scaling is performed depending on both the sign of each gradient element and an error between the continuous input and discrete output of the discretizer. We adjust a scaling factor adaptively using Hessian information of a network. We show extensive experimental results on the image classification datasets, including CIFAR-10 and ImageNet, with diverse network architectures under a wide range of bit-width settings, demonstrating the effectiveness of our method.

Related papers

• WiNet: Wavelet-based Incremental Learning for Efficient Medical Image Registration [68.25711405944239]
  Deep image registration has demonstrated exceptional accuracy and fast inference. Recent advances have adopted either multiple cascades or pyramid architectures to estimate dense deformation fields in a coarse-to-fine manner. We introduce a model-driven WiNet that incrementally estimates scale-wise wavelet coefficients for the displacement/velocity field across various scales.
  arXiv  Detail & Related papers  (2024-07-18T11:51:01Z)
• QGait: Toward Accurate Quantization for Gait Recognition with Binarized Input [17.017127559393398]
  We propose a differentiable soft quantizer, which better simulates the gradient of the round function during backpropagation. This enables the network to learn from subtle input perturbations. We further refine the training strategy to ensure convergence while simulating quantization errors.
  arXiv  Detail & Related papers  (2024-05-22T17:34:18Z)
• Adaptive Multilevel Neural Networks for Parametric PDEs with Error Estimation [0.0]
  A neural network architecture is presented to solve high-dimensional parameter-dependent partial differential equations (pPDEs) It is constructed to map parameters of the model data to corresponding finite element solutions. It outputs a coarse grid solution and a series of corrections as produced in an adaptive finite element method (AFEM)
  arXiv  Detail & Related papers  (2024-03-19T11:34:40Z)
• Effective Invertible Arbitrary Image Rescaling [77.46732646918936]
  Invertible Neural Networks (INN) are able to increase upscaling accuracy significantly by optimizing the downscaling and upscaling cycle jointly. A simple and effective invertible arbitrary rescaling network (IARN) is proposed to achieve arbitrary image rescaling by training only one model in this work. It is shown to achieve a state-of-the-art (SOTA) performance in bidirectional arbitrary rescaling without compromising perceptual quality in LR outputs.
  arXiv  Detail & Related papers  (2022-09-26T22:22:30Z)
• Scale Attention for Learning Deep Face Representation: A Study Against Visual Scale Variation [69.45176408639483]
  We reform the conv layer by resorting to the scale-space theory. We build a novel style named SCale AttentioN Conv Neural Network (textbfSCAN-CNN) As a single-shot scheme, the inference is more efficient than multi-shot fusion.
  arXiv  Detail & Related papers  (2022-09-19T06:35:04Z)
• Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss [61.26793005355441]
  Cluster-Promoting Quantization (CPQ) finds the optimal quantization grids for neural networks. DropBits is a new bit-drop technique that revises the standard dropout regularization to randomly drop bits instead of neurons. We experimentally validate our method on various benchmark datasets and network architectures.
  arXiv  Detail & Related papers  (2021-09-05T15:15:07Z)
• Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks [73.29587731448345]
  This paper proposes two novel techniques to train deep convolutional neural networks with low bit-width weights and activations. First, to obtain low bit-width weights, most existing methods obtain the quantized weights by performing quantization on the full-precision network weights. Second, to obtain low bit-width activations, existing works consider all channels equally.
  arXiv  Detail & Related papers  (2020-12-26T15:21:18Z)
• QuantNet: Learning to Quantize by Learning within Fully Differentiable Framework [32.465949985191635]
  This paper proposes a meta-based quantizer named QuantNet, which utilizes a differentiable sub-network to directly binarize the full-precision weights. Our method not only solves the problem of gradient mismatching, but also reduces the impact of discretization errors, caused by the binarizing operation in the deployment.
  arXiv  Detail & Related papers  (2020-09-10T01:41:05Z)
• AUSN: Approximately Uniform Quantization by Adaptively Superimposing Non-uniform Distribution for Deep Neural Networks [0.7378164273177589]
  Existing uniform and non-uniform quantization methods exhibit an inherent conflict between the representing range and representing resolution. We propose a novel quantization method to quantize the weight and activation. The key idea is to Approximate the Uniform quantization by Adaptively Superposing multiple Non-uniform quantized values, namely AUSN.
  arXiv  Detail & Related papers  (2020-07-08T05:10:53Z)
• Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio [101.84651388520584]
  This paper presents a new framework named network adjustment, which considers network accuracy as a function of FLOPs. Experiments on standard image classification datasets and a wide range of base networks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-04-06T15:51:00Z)
• WaveQ: Gradient-Based Deep Quantization of Neural Networks through Sinusoidal Adaptive Regularization [8.153944203144988]
  We propose a novel sinusoidal regularization, called SINAREQ, for deep quantized training. We show how SINAREQ balance compute efficiency and accuracy, and provide a heterogeneous bitwidth assignment for quantization of a large variety of deep networks.
  arXiv  Detail & Related papers  (2020-02-29T01:19:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.