상세정보
학술지
Imbalanced Classification via Feature Dictionary-based Minority Oversampling
- 발행일
- 202204
- 출처
- IEEE Access, v.10, pp.34236-34245
- ISSN
- 2169-3536
- 출판사
- IEEE
- 협약과제
- 22ZS1100, 자율성장형 복합인공지능 원천기술 연구, 송화전
- 초록
- Image classification research is one of the fields continuously studied in the computer vision domain, and several related studies have been actively conducted until recently. However, a limit exists regarding the prediction performance of real-world datasets due to the data imbalance problem between classes. Data augmentation through artificial sample generation for minority classes is one of the methods used to overcome this limitation. Among the various oversampling methods, we propose the feature dictionary-based generative model for the oversampling method. Feature dictionaries are built through the pretrained feature extractor, and the proposed generative model synthesizes artificial samples based on the dictionary. Class-to-class balanced training can be conducted by fine-tuning the classifier as additional data for the minority class. We experiment by applying the proposed framework to the fashion dataset, which has an extreme class imbalance. The experimental results demonstrate that the proposed model achieved the highest top-1 performance on various public fashion datasets. In addition, we analyze the number of samples in the dictionary and test the effectiveness of the elements that comprise the proposed model using various ablation studies.
- KSP 제안 키워드
- Classification Research, Computer Vision(CV), Data Augmentation, Data imbalance, Image classification, Imbalance problem, Imbalanced classification, Minority class, Oversampling method, Proposed model, Real-world
본 저작물은 크리에이티브 커먼즈 저작자 표시 (CC BY) 조건에 따라 이용할 수 있습니다.
