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.
Original language | English |
---|---|
Title of host publication | 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2015) |
Editors | Kristen Grauman, Erik Learned-Miller, Antonio Torralba, Andrew Zisserman |
Place of Publication | Piscataway NJ USA |
Publisher | IEEE, Institute of Electrical and Electronics Engineers |
Pages | 46-52 |
Number of pages | 7 |
ISBN (Print) | 9781467367608 |
DOIs | |
Publication status | Published - 19 Oct 2015 |
Externally published | Yes |
Event | IEEE Conference on Computer Vision and Pattern Recognition Workshops 2015 - Boston, United States of America Duration: 11 Jun 2015 → 12 Jun 2015 http://www.pamitc.org/cvpr15/ |
Conference
Conference | IEEE Conference on Computer Vision and Pattern Recognition Workshops 2015 |
---|---|
Abbreviated title | CVPRW 2015 |
Country/Territory | United States of America |
City | Boston |
Period | 11/06/15 → 12/06/15 |
Internet address |
Keywords
- Accuracy
- Australia
- Birds
- Feature extraction
- Learning systems
- Neural networks
- Training