Exploring Misclassification Information for Fine-Grained Image Classification
Open Access
- 18 June 2021
- Vol. 21 (12), 4176
- https://doi.org/10.3390/s21124176
Abstract
Fine-grained image classification is a hot topic that has been widely studied recently. Many fine-grained image classification methods ignore misclassification information, which is important to improve classification accuracy. To make use of misclassification information, in this paper, we propose a novel fine-grained image classification method by exploring the misclassification information (FGMI) of prelearned models. For each class, we harvest the confusion information from several prelearned fine-grained image classification models. For one particular class, we select a number of classes which are likely to be misclassified with this class. The images of selected classes are then used to train classifiers. In this way, we can reduce the influence of irrelevant images to some extent. We use the misclassification information for all the classes by training a number of confusion classifiers. The outputs of these trained classifiers are combined to represent images and produce classifications. To evaluate the effectiveness of the proposed FGMI method, we conduct fine-grained classification experiments on several public image datasets. Experimental results prove the usefulness of the proposed method.Keywords
Funding Information
- National Natural Science Foundation of China (61773325, 61806173)
- Joint Funds of 5th Round of Health and Education Research Program of Fujian Province (2019-WJ-41, 2017Y9059)
- Natural Science Foundation of Fujian Province (2019J05123)
This publication has 55 references indexed in Scilit:
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Contextualizing Object Detection and ClassificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Image classification by non-negative sparse coding, correlation constrained low-rank and sparse decompositionComputer Vision and Image Understanding, 2014
- Object categorization in sub-semantic spaceNeurocomputing, 2014
- Exploiting Web Images for Semantic Video Indexing Via Robust Sample-Specific LossIEEE Transactions on Multimedia, 2014
- Dynamic Label Propagation for Semi-supervised Multi-class Multi-label ClassificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- 3D Object Representations for Fine-Grained CategorizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Towards optimizing human labeling for interactive image taggingACM Transactions on Multimedia Computing, Communications, and Applications, 2013
- Image Classification with the Fisher Vector: Theory and PracticeInternational Journal of Computer Vision, 2013
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004