Subset Feature Learning for Fine-Grained Category Classification

ZongYuan Ge, Christopher McCool, Conrad Sanderson, Peter Corke; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2015, pp. 46-52

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Ge_2015_CVPR_Workshops,
author = {Ge, ZongYuan and McCool, Christopher and Sanderson, Conrad and Corke, Peter},
title = {Subset Feature Learning for Fine-Grained Category Classification},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2015}
}