arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.05941cs.LG
收藏

基于一维卷积神经网络的多尺度标签关系学习

Multi-Scale Label Relation Learning for Multi-Label Classification Using 1-Dimensional Convolutional Neural Networks

Handong Global University(韩东全球大学)

Junhyung Kim, Byungyoon Park, Charmgil Hong

摘要:

我们提出了多尺度标签依赖关系网络(MSDN),这是一种使用一维卷积核来学习多尺度标签依赖关系的多标签分类(MLC)新方法。现代多标签分类器一直采用递归神经网络(RNN)作为记忆结构来捕获和利用标签依赖关系。然而,基于RNN的MLC模型往往会引入大量的参数,这些参数可能会导致欠拟合/过拟合问题。所提出的方法使用1维卷积神经网络(1D-CNN),以更有效的方式服务于相同的目的。通过训练具有多个内核大小的模型,该方法能够学习多个尺度下标签之间的依赖关系,同时使用的参数数量要少得多。通过公共基准数据集,我们证明了与基于RNN的MLC模型相比,我们的模型可以用更少的模型参数实现更好的精度。

英文摘要:

We present Multi-Scale Label Dependence Relation Networks (MSDN), a novel approach to multi-label classification (MLC) using 1-dimensional convolution kernels to learn label dependencies at multi-scale. Modern multi-label classifiers have been adopting recurrent neural networks (RNNs) as a memory structure to capture and exploit label dependency relations. The RNN-based MLC models however tend to introduce a very large number of parameters that may cause under-/over-fitting problems. The proposed method uses the 1-dimensional convolutional neural network (1D-CNN) to serve the same purpose in a more efficient manner. By training a model with multiple kernel sizes, the method is able to learn the dependency relations among labels at multiple scales, while it uses a drastically smaller number of parameters. With public benchmark datasets, we demonstrate that our model can achieve better accuracies with much smaller number of model parameters compared to RNN-based MLC models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑