.png){kind=icon}
返回
Dual-discriminator adversarial framework for data-free quantization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2022.09.076.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Thanks to the potential to address the privacy and security issues, data-free quantization that generates samples based on the prior information in the model has recently been widely investigated. However, existing methods failed to adequately utilize the prior information and thus cannot fully restore the real-data characteristics and provide effective supervision to the quantized model, resulting in poor performance. In this paper, we propose Dual-Discriminator Adversarial Quantization (DDAQ), a novel data-free quantization framework with an adversarial learning style that enables effective sample generation and learning of the quantized model. Specifically, we employ a generator to produce meaningful and diverse samples directed by two discriminators, aiming to facilitate the matching of the batch normalization (BN) distribution and maximizing the discrepancy between the full-precision model and the quantized model, respectively. Moreover, inspired by mixed-precision quantization, i.e., the importance of each layer is different, we introduce layer importance prior to both discriminators, allowing us to make better use of the information in the model. Subsequently, the quantized model is trained with the generated samples under the supervision of the full-precision model. We evaluate DDAQ on various network structures for different vision tasks, including image classification and object detection, and the experimental results show that DDAQ outperforms all baseline methods with good generality. (C) 2022 Elsevier B.V. All rights reserved.
Keyword:
Model compression
Quantized neural networks
Data-free quantization
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
HRel: Filter pruning based on High Relevance between activation maps and class labels.png)
NEURAL NETWORKS
OAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏Pruning and quantization for deep neural network acceleration: A survey用于深度神经网络加速的修剪和量化: 一项调查NEUROCOMPUTINGOAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏Designing efficient convolutional neural network structure: A survey设计高效的卷积神经网络结构: 综述NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容