L. Zhang, C. Zhang, S. Quan, H. Xiao, G. Kuang and L. Liu, "A Class Imbalance Loss for Imbalanced Object Recognition," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13, pp. 2778-2792, 2020, doi: 10.1109/JSTARS.2020.2995703
A class imbalance loss for imbalanced object recognition
|Author:||Zhang, Linbin1; Zhang, Caiguang1; Quan, Sinong1;|
1State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, China
2College of System Engineering, National University of Defense Technology, Changsha 410073, China
3Center for Machine Vision and Signal Analysis, University of Oulu 90570, Oulu, Finland
|Online Access:||PDF Full Text (PDF, 3 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2020112092124
Institute of Electrical and Electronics Engineers,
|Publish Date:|| 2020-11-20
The class imbalance problem exists widely in vision data. In these imbalanced datasets, the majority classes dominate the loss and influence the gradient. Hence, these datasets have a significantly negative impact on the performance of many state-of-the-art methods. In this article, we propose a class imbalance loss (CI loss) to handle this problem. To distinguish imbalanced datasets in accordance with the extent of imbalance, we also define an imbalance degree that works as a decision index factor in the CI loss. Because the minority classes with fewer samples probably lose chances in descending the gradient in the training process, CI loss is introduced to make these minority classes descend further than the majority classes. In view of the imbalanced distribution of data in few-shot learning, a method for generating an imbalanced few-shot learning dataset is presented in this article. We conducted a large number of experiments in the MiniImageNet dataset, which showed the effectiveness of an algorithm for model-agnostic metalearning for rapid adaptation with CI loss. In the problem of detecting 15 ship categories, our loss function is transplanted to a rotational region convolutional neural network detection method and a cascade network architecture and achieves higher mean average precision than focal loss and cross-entropy loss. In addition, the Mixed National Institute of Standards and Technology dataset and the Moving and Stationary Target Acquisition and Recognition dataset are sampled to imbalance datasets to verify the effectiveness of CI loss.
IEEE journal of selected topics in applied Earth observations and remote sensing
|Pages:||2778 - 2792|
|Type of Publication:||
A1 Journal article – refereed
|Field of Science:||
113 Computer and information sciences
This work was supported in part by the National Natural Science Foundation of China under Grant 61872379, Grant 61701508, Grant 61372163, Grant 61906206, and Grant 71701205, and in part by the Hunan Provincial Natural Science Foundation of China underGrant 2018JJ3613.
© The Authors 2020. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.