Commonsense Oriented Fine-Grained Data Augmentation

被引：0

作者：

Li, Huachao ^{[1
]}

Kang, Bin ^{[1
]}

Wang, Lei ^{[2
]}

机构：

[1] School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing,210003, China

[2] School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing,210003, China

来源：

Computer Engineering and Applications | 2024年 / 60卷 / 06期

关键词：

The representative researches on data augmentation are mainly carried out on common classification benchmark datasets such as ImageNet. Considering intra- class and inter- class relation in fine- grained visual classification (FGVC) datasets is so different from ordinary classification datasets; data augmentation methods for FGVC need to be further studied. Therefore; this paper proposes a fine- grained semantic image patch mixing method by commonsense (ComSipmix); starting from the fine-grained recognition task and the special properties of the dataset. The proposed method exploits common sense knowledge to mine potential associations between sample labels; and designs a multi-branch convolutional neural network structure for structured image mixing strategy based on this; so that the image mixing process pays more attention to the subtle differences of targets. Through extensive performance tests; it can be verified that the performance of the proposed method is significantly better than the mainstream image mixing-based data augmentation methods. At the same time; through experimental verification; the common sense knowledge proposed in this paper helps to improve the performance of various data augmentation models based on mixed image classes. © 2017 Editorial Office of Tunnel Construction. All rights reserved;

D O I：

10.3778/j.issn.1002-8331.2210-0361

中图分类号：

学科分类号：

摘要：

引用

页码：214 / 221

共 50 条

[1] Fine-Grained Recognition With Learnable Semantic Data Augmentation
Pu, Yifan
Han, Yizeng
Wang, Yulin
Feng, Junlan
Deng, Chao
Huang, Gao
[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 33 : 3130 - 3144
[2] A Data Augmentation Based ViT for Fine-Grained Visual Classification
Yuan, Shuozhi
Guo, Wenming
Han, Fang
[J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2023, PT II, 2023, 14255 : 1 - 12
[3] WebChild 2.0: Fine-Grained Commonsense Knowledge Distillation
Tandon, Niket
de Melo, Gerard
Weikum, Gerhard
[J]. PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017): SYSTEM DEMONSTRATIONS, 2017, : 115 - 120
[4] Fine-Grained Object Detection Using Transfer Learning and Data Augmentation
Dalal, Rahul
Moh, Teng-Sheng
[J]. 2018 IEEE/ACM INTERNATIONAL CONFERENCE ON ADVANCES IN SOCIAL NETWORKS ANALYSIS AND MINING (ASONAM), 2018, : 893 - 896
[5] Class Activation Mapping Guided Data Augmentation for Fine-Grained Visual Classification
Guo W.
Wang T.
[J]. Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2021, 33 (11): : 1698 - 1704
[6] Fine-Grained Entity Typing via Label Noise Reduction and Data Augmentation
Li, Haoyang
Lin, Xueling
Chen, Lei
[J]. DATABASE SYSTEMS FOR ADVANCED APPLICATIONS (DASFAA 2021), PT I, 2021, 12681 : 356 - 374
[7] Dual attention interactive fine-grained classification network based on data augmentation
Zhu, Qiangxi
Kuang, Wenlan
Li, Zhixin
[J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2022, 88
[8] Fine-Grained Text Classification Based on Label Augmentation
Guo, Ruiqiang
Yang, Shilong
Jia, Xiaowen
Wei, Qianqiang
[J]. Computer Engineering and Applications, 60 (21): : 134 - 141
[9] Fine-Grained Crowdsourcing for Fine-Grained Recognition
Jia Deng
Krause, Jonathan
Li Fei-Fei
[J]. 2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2013, : 580 - 587
[10] Attention-Guided CutMix Data Augmentation Network for Fine-Grained Bird Recognition
Guo, Wenming
Wang, Yifei
Han, Fang
[J]. PROCEEDINGS OF 2021 2ND INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND INFORMATION SYSTEMS (ICAIIS '21), 2021,

← 1 2 3 4 5 →