From Categories to Subcateories: Large-scale Image Classification with Partial Class Label Refinement
Marko Ristin, Juergen Gall, Matthieu Guillaumin, and Luc Van Gool
Abstract
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.
Images
Given training data annotated with a set of categories like feline, our goal is to refine the classification into subcategories like cat and lion. We assume that the refined labels are available only for a subset of the training data S(fine), while for the rest, S(coarse), subcategory labels are not available.
Source Code and Data
If you have questions concerning the data, please contact Marko Ristin.
Publications
Ristin M., Gall J., Guillaumin M., and van Gool L., From Categories to Subcateories: Large-scale Image Classification with Partial Class Label Refinement (PDF), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'15), 231 - 239, 2015. ©IEEE