Fine-grained classification based on multi-scale pyramid convolution networks.

The large intra-class variance and small inter-class variance are the key factor affecting fine-grained image classification. Recently, some algorithms have been more accurate and efficient. However, these methods ignore the multi-scale information of the network, resulting in insufficient ability t...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Gaihua Wang, Lei Cheng, Jinheng Lin, Yingying Dai, Tianlun Zhang
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/8d07f016ed4944ba9cbdc2365f63a4df
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8d07f016ed4944ba9cbdc2365f63a4df
record_format	dspace
spelling	oai:doaj.org-article:8d07f016ed4944ba9cbdc2365f63a4df2021-12-02T20:09:23ZFine-grained classification based on multi-scale pyramid convolution networks.1932-620310.1371/journal.pone.0254054https://doaj.org/article/8d07f016ed4944ba9cbdc2365f63a4df2021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0254054https://doaj.org/toc/1932-6203The large intra-class variance and small inter-class variance are the key factor affecting fine-grained image classification. Recently, some algorithms have been more accurate and efficient. However, these methods ignore the multi-scale information of the network, resulting in insufficient ability to capture subtle changes. To solve this problem, a weakly supervised fine-grained classification network based on multi-scale pyramid is proposed in this paper. It uses pyramid convolution kernel to replace ordinary convolution kernel in residual network, which can expand the receptive field of the convolution kernel and use complementary information of different scales. Meanwhile, the weakly supervised data augmentation network (WS-DAN) is used to prevent over fitting and improve the performance of the model. In addition, a new attention module, which includes spatial attention and channel attention, is introduced to pay more attention to the object part in the image. The comprehensive experiments are carried out on three public benchmarks. It shows that the proposed method can extract subtle feature and achieve classification effectively.Gaihua WangLei ChengJinheng LinYingying DaiTianlun ZhangPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 7, p e0254054 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Gaihua Wang Lei Cheng Jinheng Lin Yingying Dai Tianlun Zhang Fine-grained classification based on multi-scale pyramid convolution networks.
description	The large intra-class variance and small inter-class variance are the key factor affecting fine-grained image classification. Recently, some algorithms have been more accurate and efficient. However, these methods ignore the multi-scale information of the network, resulting in insufficient ability to capture subtle changes. To solve this problem, a weakly supervised fine-grained classification network based on multi-scale pyramid is proposed in this paper. It uses pyramid convolution kernel to replace ordinary convolution kernel in residual network, which can expand the receptive field of the convolution kernel and use complementary information of different scales. Meanwhile, the weakly supervised data augmentation network (WS-DAN) is used to prevent over fitting and improve the performance of the model. In addition, a new attention module, which includes spatial attention and channel attention, is introduced to pay more attention to the object part in the image. The comprehensive experiments are carried out on three public benchmarks. It shows that the proposed method can extract subtle feature and achieve classification effectively.
format	article
author	Gaihua Wang Lei Cheng Jinheng Lin Yingying Dai Tianlun Zhang
author_facet	Gaihua Wang Lei Cheng Jinheng Lin Yingying Dai Tianlun Zhang
author_sort	Gaihua Wang
title	Fine-grained classification based on multi-scale pyramid convolution networks.
title_short	Fine-grained classification based on multi-scale pyramid convolution networks.
title_full	Fine-grained classification based on multi-scale pyramid convolution networks.
title_fullStr	Fine-grained classification based on multi-scale pyramid convolution networks.
title_full_unstemmed	Fine-grained classification based on multi-scale pyramid convolution networks.
title_sort	fine-grained classification based on multi-scale pyramid convolution networks.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/8d07f016ed4944ba9cbdc2365f63a4df
work_keys_str_mv	AT gaihuawang finegrainedclassificationbasedonmultiscalepyramidconvolutionnetworks AT leicheng finegrainedclassificationbasedonmultiscalepyramidconvolutionnetworks AT jinhenglin finegrainedclassificationbasedonmultiscalepyramidconvolutionnetworks AT yingyingdai finegrainedclassificationbasedonmultiscalepyramidconvolutionnetworks AT tianlunzhang finegrainedclassificationbasedonmultiscalepyramidconvolutionnetworks
_version_	1718375074100150272

Fine-grained classification based on multi-scale pyramid convolution networks.

Ejemplares similares