Subset Feature Learning for Fine-Grained Category Classification
Abstract
Fine-grained categorisation has been a challenging problem due to small inter-class variation, large intra-class variation and low number of training images. We propose a learning system which first clusters visually similar classes and then learns deep convolutional neural network features specific to each subset. Experiments on the popular fine-grained Caltech-UCSD bird dataset show that the proposed method outperforms recent fine-grained categorisation methods under the most difficult setting: no bounding boxes are presented at test time. It achieves a mean accuracy of 77.5%, compared to the previous best performance of 73.2%. We also show that progressive transfer learning allows us to first learn domain-generic features (for bird classification) which can then be adapted to specific set of bird classes, yielding improvements in accuracy.
Cite
Text
Ge et al. "Subset Feature Learning for Fine-Grained Category Classification." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2015. doi:10.1109/CVPRW.2015.7301271Markdown
[Ge et al. "Subset Feature Learning for Fine-Grained Category Classification." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2015.](https://mlanthology.org/cvprw/2015/ge2015cvprw-subset/) doi:10.1109/CVPRW.2015.7301271BibTeX
@inproceedings{ge2015cvprw-subset,
title = {{Subset Feature Learning for Fine-Grained Category Classification}},
author = {Ge, ZongYuan and McCool, Christopher and Sanderson, Conrad and Corke, Peter I.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2015},
pages = {46-52},
doi = {10.1109/CVPRW.2015.7301271},
url = {https://mlanthology.org/cvprw/2015/ge2015cvprw-subset/}
}