Fine-grained object recognition and zero-shot learning in multispectral imagery
| dc.contributor.author | Sümbül, Gencer | en_US |
| dc.contributor.author | Aksoy, Selim | en_US |
| dc.contributor.author | Cinbiş, R. G. | en_US |
| dc.coverage.spatial | Izmir, Turkey | en_US |
| dc.date.accessioned | 2019-02-21T16:04:52Z | |
| dc.date.available | 2019-02-21T16:04:52Z | |
| dc.date.issued | 2018 | en_US |
| dc.department | Department of Computer Engineering | en_US |
| dc.description | Date of Conference: 2-5 May 2018 | en_US |
| dc.description.abstract | We present a method for fine-grained object recognition problem, that aims to recognize the type of an object among a large number of sub-categories, and zero-shot learning scenario on multispectral images. In order to establish a relation between seen classes and new unseen classes, a compatibility function between image features extracted from a convolutional neural network and auxiliary information of classes is learnt. Knowledge transfer for unseen classes is carried out by maximizing this function. Performance of the model (15.2%) evaluated with manually annotated attributes, a natural language model, and a scientific taxonomy as auxiliary information is promisingly better than the other methods for 16 test classes. | |
| dc.identifier.doi | 10.1109/SIU.2018.8404256 | |
| dc.identifier.isbn | 9781538615010 | |
| dc.identifier.uri | http://hdl.handle.net/11693/50215 | |
| dc.language.iso | Turkish | |
| dc.publisher | IEEE | en_US |
| dc.relation.isversionof | https://doi.org/10.1109/SIU.2018.8404256 | |
| dc.source.title | 2018 26th Signal Processing and Communications Applications Conference (SIU) | en_US |
| dc.subject | Fine-grained classification | en_US |
| dc.subject | Object recognition | en_US |
| dc.subject | Zero-shot learning | en_US |
| dc.title | Fine-grained object recognition and zero-shot learning in multispectral imagery | en_US |
| dc.title.alternative | Multispektral görüntülerde ince taneli nesne tanıma ve örneksiz öğrenme | en_US |
| dc.type | Conference Paper | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Fine_grained_object_recognition_and_zero_shot_learning_in_multispectral_imagery.pdf
- Size:
- 1.79 MB
- Format:
- Adobe Portable Document Format
- Description:
- Full printable version