2024年11月16日，Elsevier 旗下top期刊《Neural Networks》在线发表了云南师范大学信息学院户战选教授团队的最新研究成果《Prototypical classifier with distribution consistency regularization for generalized category discovery: A strong baseline》。云南师范大学信息学院为户战选教授为通讯作者，合作单位为西北工业大学计算机科学学院和人工智能学院。

https://www.sciencedirect.com/science/article/abs/pii/S0893608024008372

Abstract

Generalized Category Discovery (GCD) addresses a more realistic and challenging setting in semi-supervised visual recognition, where unlabeled data contains samples from both known and novel categories. Recently, prototypical classifier has shown prominent performance on this issue, with the Softmax-based Cross-Entropy loss (SCE) commonly employed to optimize the distance between a sample and prototypes. However, the inherent non-bijectiveness of SCE prevents it from resolving intraclass relations among samples, resulting in semantic ambiguity. To mitigate this issue, we propose Distribution Consistency Regularization (DCR) for the prototypical classifier. By leveraging a simple intraclass consistency loss, we enforce the classifier to yield consistent distributions for samples belonging to the same class. In doing so, we equip the classifier to better capture local structures and alleviate semantic ambiguity. Additionally, we propose using partial labels, rather than hard pseudo labels, to explore potential positive pairs in unlabeled data, thereby reducing the risk of introducing noisy supervisory signals. DCR requires no external sophisticated module, rendering the enhanced model concise and efficient. Extensive experiments validate consistent performance benefits of DCR while achieving competitive or better performance on six benchmarks. Hence, our method can serve as a strong baseline for GCD. Our code is available at: https://github.com/yichenwang231/DCR

拓展阅读：

https://cic.ynnu.edu.cn/info/1012/2321.htm

云师大信息学院户战选在国际权威期刊《Information Fusion》发表研究成果

云师大信息学院户战选在《Information Sciences》发表最新研究成果

转载本文请联系原作者获取授权，同时请注明本文来自蒋金和科学网博客。
链接地址：https://blog.sciencenet.cn/blog-454141-1460457.html

上一篇：云师大能环学院杨培志教授、段良飞副教授课题组在《Advanced Functional Materials》发表最新成果
下一篇：云师大物电学院张伟斌、朱挺在硅酸盐top期刊《Ceramics International》发表最新研究成果