Quantization of Generative Adversarial Networks for Efficient Inference: a Methodological Study

• URL: http://arxiv.org/abs/2108.13996v1
• Date: Tue, 31 Aug 2021 17:42:24 GMT
• Title: Quantization of Generative Adversarial Networks for Efficient Inference: a Methodological Study
• Abstract summary: Generative adversarial networks (GANs) have an enormous potential impact on digital content creation, e.g., photo-realistic digital avatars, semantic content editing, and quality enhancement of speech and images. The performance of modern GANs comes together with massive amounts of computations performed during the inference and high energy consumption. In this paper, we study state-of-art quantization techniques on three diverse GAN architectures, namely StyleGAN, Self-Attention GAN, and CycleGAN.
• Score: 41.74498230885008
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Generative adversarial networks (GANs) have an enormous potential impact on digital content creation, e.g., photo-realistic digital avatars, semantic content editing, and quality enhancement of speech and images. However, the performance of modern GANs comes together with massive amounts of computations performed during the inference and high energy consumption. That complicates, or even makes impossible, their deployment on edge devices. The problem can be reduced with quantization -- a neural network compression technique that facilitates hardware-friendly inference by replacing floating-point computations with low-bit integer ones. While quantization is well established for discriminative models, the performance of modern quantization techniques in application to GANs remains unclear. GANs generate content of a more complex structure than discriminative models, and thus quantization of GANs is significantly more challenging. To tackle this problem, we perform an extensive experimental study of state-of-art quantization techniques on three diverse GAN architectures, namely StyleGAN, Self-Attention GAN, and CycleGAN. As a result, we discovered practical recipes that allowed us to successfully quantize these models for inference with 4/8-bit weights and 8-bit activations while preserving the quality of the original full-precision models.

Related papers

• Low-bit Model Quantization for Deep Neural Networks: A Survey [123.89598730307208]
  This article surveys the recent five-year progress towards low-bit quantization on deep neural networks (DNNs)<n>We discuss and compare the state-of-the-art quantization methods and classify them into 8 main categories and 24 sub-categories according to their core techniques.<n>We shed light on the potential research opportunities in the field of model quantization.
  arXiv  Detail & Related papers  (2025-05-08T13:26:19Z)
• A Distributed Hybrid Quantum Convolutional Neural Network for Medical Image Classification [1.458255172453241]
  We propose a distributed hybrid quantum convolutional neural network based on quantum circuit splitting.<n>By integrating distributed techniques based on quantum circuit splitting, the 8-qubit QCNN can be reconstructed using only 5 qubits.<n>Our model achieves strong performance across 3 datasets for both binary and multiclass classification tasks.
  arXiv  Detail & Related papers  (2025-01-07T11:58:40Z)
• Post-Training Non-Uniform Quantization for Convolutional Neural Networks [0.0]
  Quantization is a technique that aims to alleviate large storage requirements and speed up the inference process. In this paper, we introduce a novel post-training quantization method for model weights. Our method finds optimal clipping thresholds and scaling factors along with mathematical guarantees that our method minimizes quantization noise.
  arXiv  Detail & Related papers  (2024-12-10T10:33:58Z)
• Towards Scalable and Versatile Weight Space Learning [51.78426981947659]
  This paper introduces the SANE approach to weight-space learning. Our method extends the idea of hyper-representations towards sequential processing of subsets of neural network weights.
  arXiv  Detail & Related papers  (2024-06-14T13:12:07Z)
• U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation [48.40120035775506]
  Kolmogorov-Arnold Networks (KANs) reshape the neural network learning via the stack of non-linear learnable activation functions. We investigate, modify and re-design the established U-Net pipeline by integrating the dedicated KAN layers on the tokenized intermediate representation, termed U-KAN. We further delved into the potential of U-KAN as an alternative U-Net noise predictor in diffusion models, demonstrating its applicability in generating task-oriented model architectures.
  arXiv  Detail & Related papers  (2024-06-05T04:13:03Z)
• QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning [52.157939524815866]
  In this paper, we identify imbalanced activation distributions as a primary source of quantization difficulty.<n>We propose to adjust these distributions through weight finetuning to be more quantization-friendly.<n>Our method demonstrates its efficacy across three high-resolution image generation tasks.
  arXiv  Detail & Related papers  (2024-02-06T03:39:44Z)
• Variational Quantum Circuits Enhanced Generative Adversarial Network [5.209320054725053]
  We propose a hybrid quantum-classical architecture for improving GAN (denoted as QC-GAN) The QC-GAN consists of a quantum variational circuit together with a one-layer neural network, and the discriminator consists of a traditional neural network. We have also demonstrated the superiority of QC-GAN over an alternative quantum GAN, namely pathGAN, which could hardly generate 16$times$16 or larger images.
  arXiv  Detail & Related papers  (2024-02-02T03:59:35Z)
• PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators [120.06891448820447]
  How to obtain clear and visually pleasant images has become a common concern of people. The task of underwater image enhancement (UIE) has also emerged as the times require. In this paper, we propose a physical model-guided GAN model for UIE, referred to as PUGAN. Our PUGAN outperforms state-of-the-art methods in both qualitative and quantitative metrics.
  arXiv  Detail & Related papers  (2023-06-15T07:41:12Z)
• Resource Saving via Ensemble Techniques for Quantum Neural Networks [1.4606049539095878]
  We propose the use of ensemble techniques, which involve constructing a single machine learning model based on multiple instances of quantum neural networks. In particular, we implement bagging and AdaBoost techniques, with different data loading configurations, and evaluate their performance on both synthetic and real-world classification and regression tasks. Our findings indicate that these methods enable the construction of large, powerful models even on relatively small quantum devices.
  arXiv  Detail & Related papers  (2023-03-20T17:19:45Z)
• PowerQuant: Automorphism Search for Non-Uniform Quantization [37.82255888371488]
  We identify the uniformity of the quantization operator as a limitation of existing approaches, and propose a data-free non-uniform method. We show that our approach, dubbed PowerQuant, only require simple modifications in the quantized DNN activation functions.
  arXiv  Detail & Related papers  (2023-01-24T08:30:14Z)
• Low-bit Shift Network for End-to-End Spoken Language Understanding [7.851607739211987]
  We propose the use of power-of-two quantization, which quantizes continuous parameters into low-bit power-of-two values. This reduces computational complexity by removing expensive multiplication operations and with the use of low-bit weights.
  arXiv  Detail & Related papers  (2022-07-15T14:34:22Z)
• 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)
• Learning Frequency-aware Dynamic Network for Efficient Super-Resolution [56.98668484450857]
  This paper explores a novel frequency-aware dynamic network for dividing the input into multiple parts according to its coefficients in the discrete cosine transform (DCT) domain. In practice, the high-frequency part will be processed using expensive operations and the lower-frequency part is assigned with cheap operations to relieve the computation burden. Experiments conducted on benchmark SISR models and datasets show that the frequency-aware dynamic network can be employed for various SISR neural architectures.
  arXiv  Detail & Related papers  (2021-03-15T12:54:26Z)
• Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search [112.05977301976613]
  We propose to combine Network Architecture Search methods with quantization to enjoy the merits of the two sides. We first propose the joint training of architecture and quantization with a shared step size to acquire a large number of quantized models. Then a bit-inheritance scheme is introduced to transfer the quantized models to the lower bit, which further reduces the time cost and improves the quantization accuracy.
  arXiv  Detail & Related papers  (2020-10-09T03:52:16Z)

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.