Annotation Cost Efficient Active Learning for Content Based Image Retrieval ...
Deep metric learning (DML) based methods have been found very effective for content-based image retrieval (CBIR) in remote sensing (RS). For accurately learning the model parameters of deep neural networks, most of the DML methods require a high number of annotated training images, which can be cost...
Main Authors: | , , , , |
---|---|
Format: | Report |
Language: | unknown |
Published: |
arXiv
2023
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2306.11605 https://arxiv.org/abs/2306.11605 |
id |
ftdatacite:10.48550/arxiv.2306.11605 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2306.11605 2023-07-23T04:19:01+02:00 Annotation Cost Efficient Active Learning for Content Based Image Retrieval ... Henkel, Julia Hoxha, Genc Sumbul, Gencer Möllenbrok, Lars Demir, Begüm 2023 https://dx.doi.org/10.48550/arxiv.2306.11605 https://arxiv.org/abs/2306.11605 unknown arXiv Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences CreativeWork Preprint article Article 2023 ftdatacite https://doi.org/10.48550/arxiv.2306.11605 2023-07-03T21:56:53Z Deep metric learning (DML) based methods have been found very effective for content-based image retrieval (CBIR) in remote sensing (RS). For accurately learning the model parameters of deep neural networks, most of the DML methods require a high number of annotated training images, which can be costly to gather. To address this problem, in this paper we present an annotation cost efficient active learning (AL) method (denoted as ANNEAL). The proposed method aims to iteratively enrich the training set by annotating the most informative image pairs as similar or dissimilar, while accurately modelling a deep metric space. This is achieved by two consecutive steps. In the first step the pairwise image similarity is modelled based on the available training set. Then, in the second step the most uncertain and diverse (i.e., informative) image pairs are selected to be annotated. Unlike the existing AL methods for CBIR, at each AL iteration of ANNEAL a human expert is asked to annotate the most informative image ... : Accepted at IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2023. Our code is available at https://git.tu-berlin.de/rsim/ANNEAL ... Report DML DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences |
spellingShingle |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences Henkel, Julia Hoxha, Genc Sumbul, Gencer Möllenbrok, Lars Demir, Begüm Annotation Cost Efficient Active Learning for Content Based Image Retrieval ... |
topic_facet |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences |
description |
Deep metric learning (DML) based methods have been found very effective for content-based image retrieval (CBIR) in remote sensing (RS). For accurately learning the model parameters of deep neural networks, most of the DML methods require a high number of annotated training images, which can be costly to gather. To address this problem, in this paper we present an annotation cost efficient active learning (AL) method (denoted as ANNEAL). The proposed method aims to iteratively enrich the training set by annotating the most informative image pairs as similar or dissimilar, while accurately modelling a deep metric space. This is achieved by two consecutive steps. In the first step the pairwise image similarity is modelled based on the available training set. Then, in the second step the most uncertain and diverse (i.e., informative) image pairs are selected to be annotated. Unlike the existing AL methods for CBIR, at each AL iteration of ANNEAL a human expert is asked to annotate the most informative image ... : Accepted at IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2023. Our code is available at https://git.tu-berlin.de/rsim/ANNEAL ... |
format |
Report |
author |
Henkel, Julia Hoxha, Genc Sumbul, Gencer Möllenbrok, Lars Demir, Begüm |
author_facet |
Henkel, Julia Hoxha, Genc Sumbul, Gencer Möllenbrok, Lars Demir, Begüm |
author_sort |
Henkel, Julia |
title |
Annotation Cost Efficient Active Learning for Content Based Image Retrieval ... |
title_short |
Annotation Cost Efficient Active Learning for Content Based Image Retrieval ... |
title_full |
Annotation Cost Efficient Active Learning for Content Based Image Retrieval ... |
title_fullStr |
Annotation Cost Efficient Active Learning for Content Based Image Retrieval ... |
title_full_unstemmed |
Annotation Cost Efficient Active Learning for Content Based Image Retrieval ... |
title_sort |
annotation cost efficient active learning for content based image retrieval ... |
publisher |
arXiv |
publishDate |
2023 |
url |
https://dx.doi.org/10.48550/arxiv.2306.11605 https://arxiv.org/abs/2306.11605 |
genre |
DML |
genre_facet |
DML |
op_rights |
Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 |
op_doi |
https://doi.org/10.48550/arxiv.2306.11605 |
_version_ |
1772181769953476608 |