DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization

• URL: http://arxiv.org/abs/2208.09708v3
• Date: Tue, 24 Oct 2023 16:22:40 GMT
• Title: DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization
• Authors: Xinlin Li, Bang Liu, Rui Heng Yang, Vanessa Courville, Chao Xing, Vahid Partovi Nia
• Abstract summary: We propose the DenseShift network, which significantly improves the accuracy of Shift networks. Our experiments on various computer vision and speech tasks demonstrate that DenseShift outperforms existing low-bit multiplication-free networks.
• Score: 27.231327287238102
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Efficiently deploying deep neural networks on low-resource edge devices is challenging due to their ever-increasing resource requirements. To address this issue, researchers have proposed multiplication-free neural networks, such as Power-of-Two quantization, or also known as Shift networks, which aim to reduce memory usage and simplify computation. However, existing low-bit Shift networks are not as accurate as their full-precision counterparts, typically suffering from limited weight range encoding schemes and quantization loss. In this paper, we propose the DenseShift network, which significantly improves the accuracy of Shift networks, achieving competitive performance to full-precision networks for vision and speech applications. In addition, we introduce a method to deploy an efficient DenseShift network using non-quantized floating-point activations, while obtaining 1.6X speed-up over existing methods. To achieve this, we demonstrate that zero-weight values in low-bit Shift networks do not contribute to model capacity and negatively impact inference computation. To address this issue, we propose a zero-free shifting mechanism that simplifies inference and increases model capacity. We further propose a sign-scale decomposition design to enhance training efficiency and a low-variance random initialization strategy to improve the model's transfer learning performance. Our extensive experiments on various computer vision and speech tasks demonstrate that DenseShift outperforms existing low-bit multiplication-free networks and achieves competitive performance compared to full-precision networks. Furthermore, our proposed approach exhibits strong transfer learning performance without a drop in accuracy. Our code was released on GitHub.

Related papers

• Learning Discrete Weights and Activations Using the Local Reparameterization Trick [21.563618480463067]
  In computer vision and machine learning, a crucial challenge is to lower the computation and memory demands for neural network inference. By binarizing the network weights and activations, one can significantly reduce computational complexity. This leads to a more efficient neural network inference that can be deployed on low-resource devices.
  arXiv  Detail & Related papers  (2023-07-04T12:27:10Z)
• Solving Large-scale Spatial Problems with Convolutional Neural Networks [88.31876586547848]
  We employ transfer learning to improve training efficiency for large-scale spatial problems. We propose that a convolutional neural network (CNN) can be trained on small windows of signals, but evaluated on arbitrarily large signals with little to no performance degradation.
  arXiv  Detail & Related papers  (2023-06-14T01:24:42Z)
• Self-Compression in Bayesian Neural Networks [0.9176056742068814]
  We propose a new insight into network compression through the Bayesian framework. We show that Bayesian neural networks automatically discover redundancy in model parameters, thus enabling self-compression. Our experimental results show that the network architecture can be successfully compressed by deleting parameters identified by the network itself.
  arXiv  Detail & Related papers  (2021-11-10T21:19:40Z)
• $S^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks [41.54155265996312]
  Shift neural networks reduce complexity by removing expensive multiplication operations and quantizing continuous weights into low-bit discrete values. Our proposed training method pushes the boundaries of shift neural networks and shows 3-bit shift networks out-performs their full-precision counterparts in terms of top-1 accuracy on ImageNet.
  arXiv  Detail & Related papers  (2021-07-07T19:33:02Z)
• ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training [68.63354877166756]
  ActNN is a memory-efficient training framework that stores randomly quantized activations for back propagation. ActNN reduces the memory footprint of the activation by 12x, and it enables training with a 6.6x to 14x larger batch size.
  arXiv  Detail & Related papers  (2021-04-29T05:50:54Z)
• ShiftAddNet: A Hardware-Inspired Deep Network [87.18216601210763]
  ShiftAddNet is an energy-efficient multiplication-less deep neural network. It leads to both energy-efficient inference and training, without compromising expressive capacity. ShiftAddNet aggressively reduces over 80% hardware-quantified energy cost of DNNs training and inference, while offering comparable or better accuracies.
  arXiv  Detail & Related papers  (2020-10-24T05:09:14Z)
• Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming [97.40955121478716]
  We propose a first-order dual SDP algorithm that requires memory only linear in the total number of network activations. We significantly improve L-inf verified robust accuracy from 1% to 88% and 6% to 40% respectively. We also demonstrate tight verification of a quadratic stability specification for the decoder of a variational autoencoder.
  arXiv  Detail & Related papers  (2020-10-22T12:32:29Z)
• ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions [76.05981545084738]
  We propose several ideas for enhancing a binary network to close its accuracy gap from real-valued networks without incurring any additional computational cost. We first construct a baseline network by modifying and binarizing a compact real-valued network with parameter-free shortcuts. We show that the proposed ReActNet outperforms all the state-of-the-arts by a large margin.
  arXiv  Detail & Related papers  (2020-03-07T02:12:02Z)
• Widening and Squeezing: Towards Accurate and Efficient QNNs [125.172220129257]
  Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters. Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques. We address this problem by projecting features in original full-precision networks to high-dimensional quantization features.
  arXiv  Detail & Related papers  (2020-02-03T04:11:13Z)
• Mixed-Precision Quantized Neural Network with Progressively Decreasing Bitwidth For Image Classification and Object Detection [21.48875255723581]
  A mixed-precision quantized neural network with progressively ecreasing bitwidth is proposed to improve the trade-off between accuracy and compression. Experiments on typical network architectures and benchmark datasets demonstrate that the proposed method could achieve better or comparable results.
  arXiv  Detail & Related papers  (2019-12-29T14:11:33Z)

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.