论文标题
部分可观测时空混沌系统的无模型预测
A Deep Model for Partial Multi-Label Image Classification with Curriculum Based Disambiguation
论文作者
论文摘要
在本文中，我们研究了部分多标签（PML）图像分类问题，其中每个图像都用候选标签集注释，由多个相关标签和其他嘈杂标签组成。现有的PML方法通常会设计一种歧义策略来通过利用具有额外假设的先验知识来滤除嘈杂的标签，这在许多实际任务中都无法使用。此外，由于歧义的目标函数通常是在整个训练集中精心设计的，因此在小型批次上使用SGD的深层模型中几乎无法优化它。在本文中，我们首次提出了一个深层模型，以增强表示能力和歧视能力。一方面，我们提出了一种新型的基于课程的歧义策略，以通过融合不同类别的各种困难来逐步识别地面真相标签。另一方面，引入了一个一致性正则化，以供模型再培训，以平衡拟议的易于标签并利用潜在的相关标签。对常用基准数据集的广泛实验结果表明，所提出的方法显着胜过SOTA方法。
In this paper, we study the partial multi-label (PML) image classification problem, where each image is annotated with a candidate label set consists of multiple relevant labels and other noisy labels. Existing PML methods typically design a disambiguation strategy to filter out noisy labels by utilizing prior knowledge with extra assumptions, which unfortunately is unavailable in many real tasks. Furthermore, because the objective function for disambiguation is usually elaborately designed on the whole training set, it can be hardly optimized in a deep model with SGD on mini-batches. In this paper, for the first time we propose a deep model for PML to enhance the representation and discrimination ability. On one hand, we propose a novel curriculum based disambiguation strategy to progressively identify ground-truth labels by incorporating the varied difficulties of different classes. On the other hand, a consistency regularization is introduced for model retraining to balance fitting identified easy labels and exploiting potential relevant labels. Extensive experimental results on the commonly used benchmark datasets show the proposed method significantly outperforms the SOTA methods.
