Weakly Supervised Learning for Object Localization Based on an Attention Mechanism

Recently, deep learning has been successfully applied to object detection and localization tasks in images. When setting up deep learning frameworks for supervised training with large datasets, strongly labeling the objects facilitates good performance; however, the complexity of the image scene and...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Nojin Park, Hanseok Ko
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	weakly supervised object localization attention mechanism joint training Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/76e39bd9a5a04c889c7bb8e6da6d03ba
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:76e39bd9a5a04c889c7bb8e6da6d03ba
record_format	dspace
spelling	oai:doaj.org-article:76e39bd9a5a04c889c7bb8e6da6d03ba2021-11-25T16:41:45ZWeakly Supervised Learning for Object Localization Based on an Attention Mechanism10.3390/app1122109532076-3417https://doaj.org/article/76e39bd9a5a04c889c7bb8e6da6d03ba2021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10953https://doaj.org/toc/2076-3417Recently, deep learning has been successfully applied to object detection and localization tasks in images. When setting up deep learning frameworks for supervised training with large datasets, strongly labeling the objects facilitates good performance; however, the complexity of the image scene and large size of the dataset make this a laborious task. Hence, it is of paramount importance that the expensive work associated with the tasks involving strong labeling, such as bounding box annotation, is reduced. In this paper, we propose a method to perform object localization tasks without bounding box annotation in the training process by means of employing a two-path activation-map-based classifier framework. In particular, we develop an activation-map-based framework to judicially control the attention map in the perception branch by adding a two-feature extractor so that better attention weights can be distributed to induce improved performance. The experimental results indicate that our method surpasses the performance of the existing deep learning models based on weakly supervised object localization. The experimental results show that the proposed method achieves the best performance, with 75.21% Top-1 classification accuracy and 55.15% Top-1 localization accuracy on the CUB-200-2011 dataset.Nojin ParkHanseok KoMDPI AGarticleweakly supervised object localizationattention mechanismjoint trainingTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10953, p 10953 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	weakly supervised object localization attention mechanism joint training Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	weakly supervised object localization attention mechanism joint training Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Nojin Park Hanseok Ko Weakly Supervised Learning for Object Localization Based on an Attention Mechanism
description	Recently, deep learning has been successfully applied to object detection and localization tasks in images. When setting up deep learning frameworks for supervised training with large datasets, strongly labeling the objects facilitates good performance; however, the complexity of the image scene and large size of the dataset make this a laborious task. Hence, it is of paramount importance that the expensive work associated with the tasks involving strong labeling, such as bounding box annotation, is reduced. In this paper, we propose a method to perform object localization tasks without bounding box annotation in the training process by means of employing a two-path activation-map-based classifier framework. In particular, we develop an activation-map-based framework to judicially control the attention map in the perception branch by adding a two-feature extractor so that better attention weights can be distributed to induce improved performance. The experimental results indicate that our method surpasses the performance of the existing deep learning models based on weakly supervised object localization. The experimental results show that the proposed method achieves the best performance, with 75.21% Top-1 classification accuracy and 55.15% Top-1 localization accuracy on the CUB-200-2011 dataset.
format	article
author	Nojin Park Hanseok Ko
author_facet	Nojin Park Hanseok Ko
author_sort	Nojin Park
title	Weakly Supervised Learning for Object Localization Based on an Attention Mechanism
title_short	Weakly Supervised Learning for Object Localization Based on an Attention Mechanism
title_full	Weakly Supervised Learning for Object Localization Based on an Attention Mechanism
title_fullStr	Weakly Supervised Learning for Object Localization Based on an Attention Mechanism
title_full_unstemmed	Weakly Supervised Learning for Object Localization Based on an Attention Mechanism
title_sort	weakly supervised learning for object localization based on an attention mechanism
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/76e39bd9a5a04c889c7bb8e6da6d03ba
work_keys_str_mv	AT nojinpark weaklysupervisedlearningforobjectlocalizationbasedonanattentionmechanism AT hanseokko weaklysupervisedlearningforobjectlocalizationbasedonanattentionmechanism
_version_	1718413026168668160

Weakly Supervised Learning for Object Localization Based on an Attention Mechanism

Ejemplares similares