WEAKLY SUPERVISED DEEP CONVOLUTIONAL NETWORKS FOR FINE-GRAINED OBJECT RECOGNITION IN MULTISPECTRAL IMAGES

Date

2019-01-01

Author

Aygunes, Bulut
AKSOY, SELİM
Cinbiş, Ramazan Gökberk

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

15
views

24
downloads

Cite This

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.

Subject Keywords

Weakly Supervised Learning, Object Recognition, Multispectral Image Analysis

URI

https://hdl.handle.net/11511/39730

Collections

Department of Computer Engineering, Conference / Seminar