| Self Adaptive Threshold Pseudo-labeling and Unreliable Sample Contrastive Loss for Semi-supervised Image Classification | |
| Zhang, Xuerong1; Huang, Li2; Lv, Jing1; Yang, Ming1 | |
| 2024 | |
| 会议名称 | 33rd International Conference on Artificial Neural Networks and Machine Learning (ICANN) |
| 会议录名称 | SPRINGER INTERNATIONAL PUBLISHING AG
 |
| 页码 | 61-75 |
| 会议日期 | SEP 17-20, 2024 |
| 会议地点 | Univ Italian Switzerland, Lugano, SWITZERLAND |
| 出版地 | CHAM |
| 摘要 | Semi-supervised learning is attracting blooming attention, due to its success in combining unlabeled data. However, pseudo-labeling-based semi-supervised approaches suffer from two problems in image classification: (1) Existing methods might fail to adopt suitable thresholds since they either use a pre-defined/fixed threshold or an ad-hoc threshold adjusting scheme, resulting in inferior performance and slow convergence. (2) Discarding unlabeled data with confidence below the thresholds results in the loss of discriminating information. To solve these issues, we develop an effective method to make sufficient use of unlabeled data. Specifically, we design a self adaptive threshold pseudo-labeling strategy, which thresholds for each class can be dynamically adjusted to increase the number of reliable samples. Meanwhile, in order to effectively utilise unlabeled data with confidence below the thresholds, we propose an unreliable sample contrastive loss to mine the discriminative information in low-confidence samples by learning the similarities and differences between sample features. We evaluate our method on several classification benchmarks under partially labeled settings and demonstrate its superiority over the other approaches. |
| 关键词 | Semi-supervised learning Pseudo-labeling Contrastive learning |
| DOI | 10.1007/978-3-031-72335-3_5 |
| 收录类别 | CPCI-S |
| 语种 | 英语 |
| WOS研究方向 | Computer Science ; Telecommunications |
| WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Computer Science, Theory & Methods ; Telecommunications |
| WOS记录号 | WOS:001331886800005 |
| 原始文献类型 | Proceedings Paper |
| EISSN | 1611-3349 |
| 引用统计 | |
| 文献类型 | 会议论文 |
| 条目标识符 | http://ir.library.ouchn.edu.cn/handle/39V7QQFX/173664 |
| 专题 | 国家开放大学江苏分部 |
| 通讯作者 | Lv, Jing |
| 作者单位 | 1.Nanjing Normal Univ, Nanjing, Peoples R China; 2.Jiangsu Open Univ, Nanjing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhang, Xuerong,Huang, Li,Lv, Jing,et al. Self Adaptive Threshold Pseudo-labeling and Unreliable Sample Contrastive Loss for Semi-supervised Image Classification[C]. CHAM,2024:61-75. |
| 条目包含的文件 | 条目无相关文件。 | |||||
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。
修改评论