Curricular-balanced long-tailed learning
文献类型：期刊论文
| 作者 | Xiang, Xiang2; Zhang, Zihan2; Chen, Xilin1 |
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2024-02-28 |
| 卷号 | 571页码:13 |
| 关键词 | Long-tailed learning Re-weighting loss Curriculum learning |
| ISSN号 | 0925-2312 |
| DOI | 10.1016/j.neucom.2023.127121 |
| 英文摘要 | The real-world data distribution is essentially long-tailed, which poses a significant challenge to the deep model. Classification models minimizing cross-entropy loss struggle to classify the tail classes, although cross-entropy training is successful on balanced data. We reveal that minimizing cross-entropy loss under long-tailed distribution leads to the Tail Collapse phenomenon, which fundamentally limits the performance of neural networks. To correct the optimization behavior of cross-entropy training, we propose a new Curricular Balanced Loss (CurB Loss) to alleviate the imbalance. The CurB loss has two factors: the re-weighting factor and the curriculum learning factor. We design the re-weighting factor based on the margin-based training that can theoretically reach the optimums of networks. Then, we incorporate the idea of Curriculum Learning into the re-weighting loss in an adaptive manner. We design the curriculum learning factor to make the model gradually emphasize the hard classes. The empirical results demonstrate the complementary of the two factors. Our method outperforms previous state-of-the-art methods by 0.9%, 2.7%, 1.2% on CIFAR10-LT, CIFAR-100-LT and ImageNet-LT, demonstrating the effectiveness of CurB Loss for long-tailed visual recognition. |
| 资助项目 | Natural Science Fund of Hubei Province[2022CFB823] ; HUST Independent Innovation Research Fund[2021XXJS096] ; Alibaba Innovation Research Program[CRAQ7WHZ11220001-20978282] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001148963100001 |
| 出版者 | ELSEVIER |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/38399]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Xiang, Xiang |
| 作者单位 | 1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing, Peoples R China 2.Huazhong Univ Sci & Technol HUST, Sch Artificial Intelligence & Automat, Natl Key Lab Multispectral Informat Intelligent Pr, Wuhan, Peoples R China |
| 推荐引用方式 GB/T 7714 | Xiang, Xiang,Zhang, Zihan,Chen, Xilin. Curricular-balanced long-tailed learning[J]. NEUROCOMPUTING,2024,571:13. |
| APA | Xiang, Xiang,Zhang, Zihan,&Chen, Xilin.(2024).Curricular-balanced long-tailed learning.NEUROCOMPUTING,571,13. |
| MLA | Xiang, Xiang,et al."Curricular-balanced long-tailed learning".NEUROCOMPUTING 571(2024):13. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。