From categories to subcategories: Large-scale image classification with partial class label refinement
From categories to subcategories: Large-scale image classification with partial class label refinement
复制标题
DOI：
10.1109/cvpr.2015.7298619
复制
发表时间：
2015-06
期刊：
影响因子：
--
通讯作者：
M. Ristin;Juergen Gall;M. Guillaumin;L. Gool
中科院分区：
文献类型：
--
作者：
M. Ristin;Juergen Gall;M. Guillaumin;L. Gool
数字图像的数量增长极其迅速，对其分类的需求也在快速增长。但是，随着更多预定义类别的图像可用，它们也变得更加多样化并涵盖更精细的语义差异。最终，类别本身需要划分为子类别，以实现语义细化。总体而言，图像分类在过去几年中已经有了显着的改进，但仍然需要大量的手动注释数据。将类别细分为子类别会使标签数量成倍增加，从而加剧标注问题。因此，我们可以期望仅针对已标记数据的子集来细化注释，并利用较粗略的标记数据来改进分类。在这项工作中，我们研究了如何使用粗略类别标签来改进子类别的分类。为此，我们采用随机森林的框架，并提出一个考虑类别和子类别之间关系的正则化目标函数。与忽略额外粗标记数据的方法相比，我们在大规模图像分类实验中实现了子类别分类准确度的相对提高，最高可达 22%。
The number of digital images is growing extremely rapidly, and so is the need for their classification. But, as more images of pre-defined categories become available, they also become more diverse and cover finer semantic differences. Ultimately, the categories themselves need to be divided into subcategories to account for that semantic refinement. Image classification in general has improved significantly over the last few years, but it still requires a massive amount of manually annotated data. Subdividing categories into subcategories multiples the number of labels, aggravating the annotation problem. Hence, we can expect the annotations to be refined only for a subset of the already labeled data, and exploit coarser labeled data to improve classification. In this work, we investigate how coarse category labels can be used to improve the classification of subcategories. To this end, we adopt the framework of Random Forests and propose a regularized objective function that takes into account relations between categories and subcategories. Compared to approaches that disregard the extra coarse labeled data, we achieve a relative improvement in subcategory classification accuracy of up to 22% in our large-scale image classification experiments.