Presentation 2023-11-16
On Food Plant Classification from Luehdorfia Japonica Images using Multi-label Classification ABN
Tsubasa Hirakawa, Takaaki Arai, Takayoshi Yamashita, Hironobu Fujiyoshi, Yuichi Oba, Hiromichi Fukui, Masaya Yago,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Butterfly is a familiar taxon. Because of the abundance of specimens and the ease of comparison between specimens, regional variation in butterfly spots is well known, which is related to various factors such as geological history, topography, climate, and food plants. In this study, we focus on the relationship between regional variation in butterfly spots and the distribution of food plants, and aim to clarify the relationship by classifying food plants based on images of butterfly spots. Specifically, we will focus on Luehdorfia japonica, a species of butterfly with known geographic variation in butterfly spots and a highly understood distribution. We will create a spotted butterfly image classification dataset based on digital specimens and collection site metadata. We show that the multi-label Attention Branch Netowrk can be trained on the dataset to accurately classify the food plants from the butterfly images, and that the analysis of the attention map provides the same basis for decision-making as the expert knowledge.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Attention Branch Network / Multi-label Classification / Visual Explanation / Luehdorfia japonica / Local Variation
Paper # PRMU2023-27
Date of Issue 2023-11-09 (PRMU)

Conference Information
Committee PRMU / IPSJ-CVIM / IPSJ-DCC / IPSJ-CGVI
Conference Date 2023/11/16(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Kunio Kashio(NTT)
Vice Chair Takuya Funatomi(NAIST) / Go Irie(Tokyo Univ. of Science)
Secretary Takuya Funatomi(Tokyo Inst. of Tech.) / Go Irie(Riken)
Assistant Kei Shimonishi(Kyoto Univ.) / Kensho Hara(AIST)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / Special Interest Group on Computer Vision and Image Media / Special Interest Group on Digital Contents Creation / Special Interest Group on Computer Graphics and Visual Informatics
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) On Food Plant Classification from Luehdorfia Japonica Images using Multi-label Classification ABN
Sub Title (in English)
Keyword(1) Attention Branch Network
Keyword(2) Multi-label Classification
Keyword(3) Visual Explanation
Keyword(4) Luehdorfia japonica
Keyword(5) Local Variation
1st Author's Name Tsubasa Hirakawa
1st Author's Affiliation Chubu University(Chubu Univ.)
2nd Author's Name Takaaki Arai
2nd Author's Affiliation Chubu University(Chubu Univ.)
3rd Author's Name Takayoshi Yamashita
3rd Author's Affiliation Chubu University(Chubu Univ.)
4th Author's Name Hironobu Fujiyoshi
4th Author's Affiliation Chubu University(Chubu Univ.)
5th Author's Name Yuichi Oba
5th Author's Affiliation Chubu University(Chubu Univ.)
6th Author's Name Hiromichi Fukui
6th Author's Affiliation Chubu University(Chubu Univ.)
7th Author's Name Masaya Yago
7th Author's Affiliation The University Museum, The University of Tokyo(Tokyo Univ.)
Date 2023-11-16
Paper # PRMU2023-27
Volume (vol) vol.123
Number (no) PRMU-266
Page pp.pp.62-67(PRMU),
#Pages 6
Date of Issue 2023-11-09 (PRMU)