Shuai Xiao
ABSTRACT
The classification research of multimedia images has always been of great concern, and related technologies are constantly being improved to increase accuracy. Adequate evaluation and mining of sample information is an important direction, but it is always a challenge. In this article, we propose a method for constructing deep learning training datasets, which fully considers the intra class and inter class features of the samples. The intra class dispersion of the sample is evaluated by the distance from the sample features to the prototype, while inter class confusion between classes is evaluated by combining the distance of the prototype in the feature space with intra class dispersion. Based on the intra class and inter class features of samples, determine the proportion of imbalanced construction to achieve the construction of imbalanced datasets. This method has the potential to be applied to different multimedia visual tasks.
- Mateusz Buda, Atsuto Maki, and Maciej A Mazurowski. 2018. A systematic study of the class imbalance problem in convolutional neural networks. Neural networks , Vol. 106 (2018), 249--259.Google Scholar
- Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang Song, and Serge Belongie. 2019. Class-balanced loss based on effective number of samples. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 9268--9277.Google ScholarCross Ref
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770--778.Google ScholarCross Ref
- Youngkyu Hong, Seungju Han, Kwanghee Choi, Seokjun Seo, Beomsu Kim, and Buru Chang. 2021. Disentangling label distribution for long-tailed visual recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 6626--6636.Google ScholarCross Ref
- Haeyong Kang, Thang Vu, and Chang D Yoo. 2021. Learning imbalanced datasets with maximum margin loss. In 2021 IEEE International Conference on Image Processing (ICIP). IEEE, 1269--1273.Google ScholarCross Ref
- Guipeng Lan, Shuai Xiao, Jiabao Wen, Desheng Chen, and Yong Zhu. 2022. Data-Driven Deepfake Forensics Model Based on Large-Scale Frequency and Noise Features. IEEE Intelligent Systems (2022).Google ScholarDigital Library
- Yang Li and Xuewei Chao. 2022. Distance-entropy: an effective indicator for selecting informative data. Frontiers in Plant Science , Vol. 12 (2022), 818895.Google ScholarCross Ref
- Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2017. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision. 2980--2988.Google ScholarCross Ref
- Ziwei Liu, Zhongqi Miao, Xiaohang Zhan, Jiayun Wang, Boqing Gong, and Stella X Yu. 2019. Large-scale long-tailed recognition in an open world. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2537--2546.Google ScholarCross Ref
- Jiawei Ren, Cunjun Yu, Xiao Ma, Haiyu Zhao, Shuai Yi, et al. 2020. Balanced meta-softmax for long-tailed visual recognition. Advances in neural information processing systems , Vol. 33 (2020), 4175--4186.Google Scholar
- Jiawei Ren, Mingyuan Zhang, Cunjun Yu, and Ziwei Liu. 2022. Balanced mse for imbalanced visual regression. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7926--7935.Google ScholarCross Ref
- Samarth Sinha, Sayna Ebrahimi, and Trevor Darrell. 2019. Variational adversarial active learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 5972--5981.Google ScholarCross Ref
- Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Daan Wierstra, et al. 2016. Matching networks for one shot learning. Advances in neural information processing systems , Vol. 29 (2016).Google Scholar
- Shuai Xiao, Guipeng Lan, Jiachen Yang, Yang Li, and Jiabao Wen. 2022. Securing the socio-cyber world: multiorder attribute node association classification for manipulated media. IEEE Transactions on Computational Social Systems 99 (2022), 1--10.Google ScholarCross Ref
- Shuai Xiao, Guipeng Lan, Jiachen Yang, Wen Lu, Qinggang Meng, and Xinbo Gao. 2023. MCS-GAN: A Different Understanding for Generalization of Deep Forgery Detection. IEEE Transactions on Multimedia (2023).Google Scholar
- Jiachen Yang, Guipeng Lan, Yang Li, Yicheng Gong, Zhuo Zhang, and Sezai Ercisli. 2022. Data quality assessment and analysis for pest identification in smart agriculture. Computers and Electrical Engineering , Vol. 103 (2022), 108322.Google ScholarDigital Library
- Donggeun Yoo and In So Kweon. 2019. Learning loss for active learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 93--102.Google ScholarCross Ref
- Weiping Yu, Taojiannan Yang, and Chen Chen. 2021. Towards resolving the challenge of long-tail distribution in UAV images for object detection. In Proceedings of the IEEE/CVF winter conference on applications of computer vision. 3258--3267.Google ScholarCross Ref
- Boyan Zhou, Quan Cui, Xiu-Shen Wei, and Zhao-Min Chen. 2020. Bbn: Bilateral-branch network with cumulative learning for long-tailed visual recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 9719--9728.Google ScholarCross Ref
Index Terms
- Intelligent Classification of Multimedia Images Based on Class Information Mining
Recommendations
Coupling different methods for overcoming the class imbalance problem
Many classification problems must deal with imbalanced datasets where one class - the majority class - outnumbers the other classes. Standard classification methods do not provide accurate predictions in this setting since classification is generally ...
Imbalanced Nodes Classification for Graph Neural Networks Based on Valuable Sample Mining
EITCE '22: Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer EngineeringNode classification is an important task in graph neural networks, but most existing studies assume that samples from different classes are balanced. However, the class imbalance problem is widespread and can seriously affect the model's performance. ...
A fuzzy twin support vector machine based on information entropy for class imbalance learning
AbstractIn real-world binary class datasets, the total number of samples may not be the same in both the classes, i.e. size of the majority class is much larger than minority class which is called as imbalance problem. In various classification problems, ...
Comments