The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
L'emplacement et la représentation des caractéristiques des parties d'un objet jouent un rôle clé dans la reconnaissance visuelle fine. Pour favoriser la précision de la reconnaissance finale sans aucune annotation de cadre/partie englobante, de nombreuses études adoptent des réseaux de localisation d'objets pour proposer des annotations de cadre/partie englobant avec uniquement des étiquettes de catégorie, puis recadrent les images en images partielles pour aider le réseau de classification à prendre la décision finale. Dans notre travail, pour proposer des images partielles plus informatives et extraire efficacement les caractéristiques discriminantes des images originales et partielles, nous proposons une approche en deux étapes qui peut fusionner les caractéristiques originales et les caractéristiques partielles en évaluant et en classant les informations des images partielles. Les résultats expérimentaux montrent que notre approche proposée atteint d'excellentes performances sur deux ensembles de données de référence, ce qui démontre son efficacité.
Kangbo SUN
Shanghai Jiao Tong University
Jie ZHU
Shanghai Jiao Tong University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Kangbo SUN, Jie ZHU, "A Two-Stage Approach for Fine-Grained Visual Recognition via Confidence Ranking and Fusion" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 12, pp. 2693-2700, December 2020, doi: 10.1587/transinf.2020EDP7024.
Abstract: Location and feature representation of object's parts play key roles in fine-grained visual recognition. To promote the final recognition accuracy without any bounding boxes/part annotations, many studies adopt object location networks to propose bounding boxes/part annotations with only category labels, and then crop the images into partial images to help the classification network make the final decision. In our work, to propose more informative partial images and effectively extract discriminative features from the original and partial images, we propose a two-stage approach that can fuse the original features and partial features by evaluating and ranking the information of partial images. Experimental results show that our proposed approach achieves excellent performance on two benchmark datasets, which demonstrates its effectiveness.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDP7024/_p
Copier
@ARTICLE{e103-d_12_2693,
author={Kangbo SUN, Jie ZHU, },
journal={IEICE TRANSACTIONS on Information},
title={A Two-Stage Approach for Fine-Grained Visual Recognition via Confidence Ranking and Fusion},
year={2020},
volume={E103-D},
number={12},
pages={2693-2700},
abstract={Location and feature representation of object's parts play key roles in fine-grained visual recognition. To promote the final recognition accuracy without any bounding boxes/part annotations, many studies adopt object location networks to propose bounding boxes/part annotations with only category labels, and then crop the images into partial images to help the classification network make the final decision. In our work, to propose more informative partial images and effectively extract discriminative features from the original and partial images, we propose a two-stage approach that can fuse the original features and partial features by evaluating and ranking the information of partial images. Experimental results show that our proposed approach achieves excellent performance on two benchmark datasets, which demonstrates its effectiveness.},
keywords={},
doi={10.1587/transinf.2020EDP7024},
ISSN={1745-1361},
month={December},}
Copier
TY - JOUR
TI - A Two-Stage Approach for Fine-Grained Visual Recognition via Confidence Ranking and Fusion
T2 - IEICE TRANSACTIONS on Information
SP - 2693
EP - 2700
AU - Kangbo SUN
AU - Jie ZHU
PY - 2020
DO - 10.1587/transinf.2020EDP7024
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2020
AB - Location and feature representation of object's parts play key roles in fine-grained visual recognition. To promote the final recognition accuracy without any bounding boxes/part annotations, many studies adopt object location networks to propose bounding boxes/part annotations with only category labels, and then crop the images into partial images to help the classification network make the final decision. In our work, to propose more informative partial images and effectively extract discriminative features from the original and partial images, we propose a two-stage approach that can fuse the original features and partial features by evaluating and ranking the information of partial images. Experimental results show that our proposed approach achieves excellent performance on two benchmark datasets, which demonstrates its effectiveness.
ER -