Treffer: 一种基于多尺度的多层卷积稀疏编码网络.

In recent years, the Multi-layer convolutional sparse coding (ML-CSC) model has been regarded as a theoretical explanation for convolutional neural networks (CNN). While the ML-CSC model performs well on datasets with high feature contrast, its performance is not satisfactory on datasets with low feature contrast. To address this issue, this paper introduces a multi-scale technique to design a multi-scale multi-layer convolutional sparse coding network (MSMCSCNet), which not only achieves better image classification results in scenarios with weak feature contrast, but also provides the model with a solid theoretical foundation and higher interpretability. Experimental results demonstrate that, without increasing the parameter count, MSMCSCNet achieves accuracy improvements of 5.75, 9.75, and 9.8 percentage points on the Cifar10, Cifar100 datasets, and the Imagenet32 subset, respectively, compared to existing ML-CSC models. Furthermore, ablation experiments further validate the effectiveness of the model's multi-scale design and feature selection mechanism. [ABSTRACT FROM AUTHOR]

多层卷积稀疏编码模型 (Multi-layer Convolutional Sparse Coding, ML-CSC) 被认为是对卷积神经网络 (Convolutional Neural Networks, CNN) 的一种理论阐释。尽管ML-CSC模型在特征对比度高的数据集上表现良好, 但 是其在特征对比度低的数据集上表现不佳。为了解决这一问题, 本文引入多尺度技术设计了一种多尺度多层卷积稀 疏编码网络 (Multi-scale Multi-layer Convolutional Sparse Coding Network, MSMCSCNet), 不仅在特征对比度较弱的情况 下得到更好的图像分类效果, 而且也使模型具有扎实的理论基础和较高的可解释性。实验结果表明, MSMCSCNet在不增加参数量的前提下, 在Cifar10、Cifar100数据集和Imagenet32数据子集上, 准确率相比现有MLCSC模型分别提高了5.75, 9.75和9.8个百分点。此外, 消融实验进一步证实了模型的多尺度设计和特征筛选模式设 计的有效性。 [ABSTRACT FROM AUTHOR]

Copyright of Journal of Guangdong University of Technology is the property of Journal of Guangdong University of Technology and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)