Weakly supervised deep convolutional networks for fine-grained object recognition in multispectral images
Date
2019
Authors
Editor(s)
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
Source Title
International Geoscience and Remote Sensing Symposium, IGARSS 2019
Print ISSN
2153-6996
Electronic ISSN
2153-7003
Publisher
Institute of Electrical and Electronics Engineers Inc.
Volume
Issue
Pages
1478 - 1481
Language
English
Type
Journal Title
Journal ISSN
Volume Title
Series
Abstract
The challenging task of training object detectors for fine-grained classification faces additional difficulties when there are registration errors between the image data and the ground truth. We propose a weakly supervised learning methodology for the classification of 40 types of trees by using fixed-sized multispectral images with a class label but with no exact knowledge of the object location. Our approach consists of an end-to-end trainable convolutional neural network with separate branches for learning class-specific and location-specific scoring of image regions. Comparative experiments show that the proposed method simultaneously learns to detect and classify the objects of interest with high accuracy.