Long-Range Zero-Shot Generative Deep Network Quantization

• URL: http://arxiv.org/abs/2211.06816v2
• Date: Thu, 17 Nov 2022 09:34:32 GMT
• Title: Long-Range Zero-Shot Generative Deep Network Quantization
• Authors: Yan Luo, Yangcheng Gao, Zhao Zhang, Haijun Zhang, Mingliang Xu, Meng Wang
• Abstract summary: Quantization approximates a deep network model with floating-point numbers by the one with low bit width numbers. We propose a novel deep network quantizer, dubbed Long-Range Zero-Shot Generative Deep Network Quantization (LRQ)
• Score: 46.67334554503704
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantization approximates a deep network model with floating-point numbers by the one with low bit width numbers, in order to accelerate inference and reduce computation. Quantizing a model without access to the original data, zero-shot quantization can be accomplished by fitting the real data distribution by data synthesis. However, zero-shot quantization achieves inferior performance compared to the post-training quantization with real data. We find it is because: 1) a normal generator is hard to obtain high diversity of synthetic data, since it lacks long-range information to allocate attention to global features; 2) the synthetic images aim to simulate the statistics of real data, which leads to weak intra-class heterogeneity and limited feature richness. To overcome these problems, we propose a novel deep network quantizer, dubbed Long-Range Zero-Shot Generative Deep Network Quantization (LRQ). Technically, we propose a long-range generator to learn long-range information instead of simple local features. In order for the synthetic data to contain more global features, long-range attention using large kernel convolution is incorporated into the generator. In addition, we also present an Adversarial Margin Add (AMA) module to force intra-class angular enlargement between feature vector and class center. As AMA increases the convergence difficulty of the loss function, which is opposite to the training objective of the original loss function, it forms an adversarial process. Furthermore, in order to transfer knowledge from the full-precision network, we also utilize a decoupled knowledge distillation. Extensive experiments demonstrate that LRQ obtains better performance than other competitors.

Related papers

• Multi-Fidelity Residual Neural Processes for Scalable Surrogate Modeling [19.60087366873302]
  Multi-fidelity surrogate modeling aims to learn an accurate surrogate at the highest fidelity level. Deep learning approaches utilize neural network based encoders and decoders to improve scalability. We propose Multi-fidelity Residual Neural Processes (MFRNP), a novel multi-fidelity surrogate modeling framework.
  arXiv  Detail & Related papers  (2024-02-29T04:40:25Z)
• LD-GAN: Low-Dimensional Generative Adversarial Network for Spectral Image Generation with Variance Regularization [72.4394510913927]
  Deep learning methods are state-of-the-art for spectral image (SI) computational tasks. GANs enable diverse augmentation by learning and sampling from the data distribution. GAN-based SI generation is challenging since the high-dimensionality nature of this kind of data hinders the convergence of the GAN training yielding to suboptimal generation. We propose a statistical regularization to control the low-dimensional representation variance for the autoencoder training and to achieve high diversity of samples generated with the GAN.
  arXiv  Detail & Related papers  (2023-04-29T00:25:02Z)
• NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction [79.13750275141139]
  This paper proposes a novel and fast self-supervised solution for sparse-view CBCT reconstruction. The desired attenuation coefficients are represented as a continuous function of 3D spatial coordinates, parameterized by a fully-connected deep neural network. A learning-based encoder entailing hash coding is adopted to help the network capture high-frequency details.
  arXiv  Detail & Related papers  (2022-09-29T04:06:00Z)
• ECQ$^{\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs [13.446502051609036]
  We develop and describe a novel quantization paradigm for deep neural networks (DNNs) Our method leverages concepts of explainable AI (XAI) and concepts of information theory. The ultimate goal is to preserve the most relevant weights in quantization clusters of highest information content.
  arXiv  Detail & Related papers  (2021-09-09T12:57:06Z)
• Investigating the Relationship Between Dropout Regularization and Model Complexity in Neural Networks [0.0]
  Dropout Regularization serves to reduce variance in Deep Learning models. We explore the relationship between the dropout rate and model complexity by training 2,000 neural networks. We build neural networks that predict the optimal dropout rate given the number of hidden units in each dense layer.
  arXiv  Detail & Related papers  (2021-08-14T23:49:33Z)
• Global Filter Networks for Image Classification [90.81352483076323]
  We present a conceptually simple yet computationally efficient architecture that learns long-term spatial dependencies in the frequency domain with log-linear complexity. Our results demonstrate that GFNet can be a very competitive alternative to transformer-style models and CNNs in efficiency, generalization ability and robustness.
  arXiv  Detail & Related papers  (2021-07-01T17:58:16Z)
• Understanding Self-supervised Learning with Dual Deep Networks [74.92916579635336]
  We propose a novel framework to understand contrastive self-supervised learning (SSL) methods that employ dual pairs of deep ReLU networks. We prove that in each SGD update of SimCLR with various loss functions, the weights at each layer are updated by a emphcovariance operator. To further study what role the covariance operator plays and which features are learned in such a process, we model data generation and augmentation processes through a emphhierarchical latent tree model (HLTM)
  arXiv  Detail & Related papers  (2020-10-01T17:51:49Z)
• Data-Free Network Quantization With Adversarial Knowledge Distillation [39.92282726292386]
  In this paper, we consider data-free network quantization with synthetic data. The synthetic data are generated from a generator, while no data are used in training the generator and in quantization. We show the gain of producing diverse adversarial samples by using multiple generators and multiple students.
  arXiv  Detail & Related papers  (2020-05-08T16:24:55Z)
• 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)

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.