Please use this identifier to cite or link to this item:
For citation please use:
Main Title: A novel active learning technique for multi-label remote sensing image scene classification
Author(s): Teshome Zegeye, Bayable
Demir, Begüm
Type: Conference Object
Language Code: en
Abstract: This paper presents a novel multi-label active learning (MLAL) technique in the framework of multi-label remote sensing (RS) image scene classification problems. The proposed MLAL technique is developed in the framework of the multi-label SVM classifier (ML-SVM). Unlike the standard AL methods, the proposed MLAL technique redefines active learning by evaluating the informativeness of each image based on its multiple land-cover classes. Accordingly, the proposed MLAL technique is based on the joint evaluation of two criteria for the selection of the most informative images: i) multi-label uncertainty and ii) multi-label diversity. The multi-label uncertainty criterion is associated to the confidence of the multi-label classification algorithm in correctly assigning multi-labels to each image, whereas multi-label diversity criterion aims at selecting a set of un-annotated images that are as more diverse as possible to reduce the redundancy among them. In order to evaluate the multi-label uncertainty of each image, we propose a novel multi-label margin sampling strategy that: 1) considers the functional distances of each image to all ML-SVM hyperplanes; and then 2) estimates the occurrence on how many times each image falls inside the margins of ML-SVMs. If the occurrence is small, the classifiers are confident to correctly classify the considered image, and vice versa. In order to evaluate the multi-label diversity of each image, we propose a novel clustering-based strategy that clusters all the images inside the margins of the ML-SVMs and avoids selecting the uncertain images from the same clusters. The joint use of the two criteria allows one to enrich the training set of images with multi-labels. Experimental results obtained on a benchmark archive with 2100 images with their multi-labels show the effectiveness of the proposed MLAL method compared to the standard AL methods that neglect the evaluation of the uncertainty and diversity on multi-labels.
Issue Date: 9-Oct-2018
Date Available: 25-Nov-2019
DDC Class: 006 Spezielle Computerverfahren
Subject(s): active learning
multi-label uncertainty
multi-label diversity
multi-label classification
remote sensing
Sponsor/Funder: EC/H2020/759764/EU/Accurate and Scalable Processing of Big Data in Earth Observation Fact Sheet/BigEarth
Proceedings Title: Proceedings of SPIE 10789 – Image and Signal Processing for Remote Sensing XXIV
Editor: Bruzzone, Lorenzo
Bovolo, Francesca
Publisher: SPIE
Publisher Place: Bellingham, Wash.
Article Number: 107890B
Publisher DOI: 10.1117/12.2500191
EISSN: 1996-756X
ISBN: 9781510621626
ISSN: 0277-786X
Notes: Copyright 2018 Society of Photo‑Optical Instrumentation Engineers (SPIE). One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this publication for a fee or for commercial purposes, and modification of the contents of the publication are prohibited.
Appears in Collections:FG Remote Sensing Image Analysis Group » Publications

Files in This Item:
File Description SizeFormat 
teshome-zegeye_demir_2018.pdfPublished paper575.98 kBAdobe PDFThumbnail

Item Export Bar

Items in DepositOnce are protected by copyright, with all rights reserved, unless otherwise indicated.