Learning enhanced features and inferring twice for fine-grained image classification

CC BY

Saved in:
Bibliographic Details
Main Authors: Xuan, Nie, Bosong, Chai, Luyao, Wang
Format: Book
Language:English
Published: Springer 2023
Subjects:
Online Access:https://dlib.phenikaa-uni.edu.vn/handle/PNK/7359
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:localhost:PNK-7359
record_format dspace
spelling oai:localhost:PNK-73592023-03-31T01:45:04Z Learning enhanced features and inferring twice for fine-grained image classification Xuan, Nie Bosong, Chai Luyao, Wang FGVC Learning enhanced features CC BY Fine-Grained Visual Categorization (FGVC) aims to distinguish between extremely similar subordinate-level categories within the same basic-level category. Existing research has proven the great importance of the discriminative features in FGVC but ignored the contributions for correct classification from other features, and the extracted features always contain more information about the obvious regions but less about subtle regions. In this paper, firstly, a novel module named forcing module is proposed to force the network to extract more diverse features for FGVC, which generates a suppression mask based on the class activation maps to suppress the most distinguishable regions, so as to force the network to extract other secondary distinguishable features as the final features. 2023-03-31T01:45:04Z 2023-03-31T01:45:04Z 2023 Book Learning enhanced features and inferring twice for fine-grained image classification https://dlib.phenikaa-uni.edu.vn/handle/PNK/7359 en application/pdf Springer
institution Digital Phenikaa
collection Digital Phenikaa
language English
topic FGVC
Learning enhanced features
spellingShingle FGVC
Learning enhanced features
Xuan, Nie
Bosong, Chai
Luyao, Wang
Learning enhanced features and inferring twice for fine-grained image classification
description CC BY
format Book
author Xuan, Nie
Bosong, Chai
Luyao, Wang
author_facet Xuan, Nie
Bosong, Chai
Luyao, Wang
author_sort Xuan, Nie
title Learning enhanced features and inferring twice for fine-grained image classification
title_short Learning enhanced features and inferring twice for fine-grained image classification
title_full Learning enhanced features and inferring twice for fine-grained image classification
title_fullStr Learning enhanced features and inferring twice for fine-grained image classification
title_full_unstemmed Learning enhanced features and inferring twice for fine-grained image classification
title_sort learning enhanced features and inferring twice for fine-grained image classification
publisher Springer
publishDate 2023
url https://dlib.phenikaa-uni.edu.vn/handle/PNK/7359
_version_ 1761912524044763136
score 8.881002