arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.00633cs.LGcs.CV
收藏

用于多标签分类的深度依赖网络

Deep Dependency Networks for Multi-Label Classification

The University of Texas at Dallas(德克萨斯大学达拉斯分校)

Shivvrat Arya, Yu Xiang, Vibhav Gogate

摘要:

我们提出了一种简单的方法,它结合了概率图模型和深度学习架构的优势,用于解决多标签分类任务,特别关注图像和视频数据。首先,我们表明,以前的方法,结合马尔可夫随机场与神经网络的性能可以适度提高利用更强大的方法,如迭代连接图传播,整数线性规划,和$\ell_1$正则化为基础的结构学习。然后,我们提出了一个新的建模框架,称为深度依赖网络,它增强了依赖网络,一个模型,很容易训练和学习更准确的依赖关系,但限于吉布斯采样推理,到输出层的神经网络。我们表明,尽管它的简单性,共同学习这种新的架构产生了显着的性能改善基线神经网络。特别是,我们对三个视频活动分类数据集:Charades,Textually Annotated Cooking Scenes(TACoS)和Wetlab,以及三个多标签图像分类数据集:MS-COCO,PASCAL VOC和NUS-WIDE的实验评估表明,深度依赖网络几乎总是优于不使用依赖网络的纯神经架构。

英文摘要:

We propose a simple approach which combines the strengths of probabilistic graphical models and deep learning architectures for solving the multi-label classification task, focusing specifically on image and video data. First, we show that the performance of previous approaches that combine Markov Random Fields with neural networks can be modestly improved by leveraging more powerful methods such as iterative join graph propagation, integer linear programming, and $\ell_1$ regularization-based structure learning. Then we propose a new modeling framework called deep dependency networks, which augments a dependency network, a model that is easy to train and learns more accurate dependencies but is limited to Gibbs sampling for inference, to the output layer of a neural network. We show that despite its simplicity, jointly learning this new architecture yields significant improvements in performance over the baseline neural network. In particular, our experimental evaluation on three video activity classification datasets: Charades, Textually Annotated Cooking Scenes (TACoS), and Wetlab, and three multi-label image classification datasets: MS-COCO, PASCAL VOC, and NUS-WIDE show that deep dependency networks are almost always superior to pure neural architectures that do not use dependency networks.

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。

↑