Timezone: »
Semi-supervised learning (SSL) has proven to be successful in overcoming labeling difficulties by leveraging unlabeled data. Previous SSL algorithms typically assume a balanced class distribution. However, real-world datasets are usually class-imbalanced, causing the performance of existing SSL algorithms to be seriously decreased. One essential reason is that pseudo-labels for unlabeled data are selected based on a fixed confidence threshold, resulting in low performance on minority classes. In this paper, we develop a simple yet effective framework, which only involves adaptive thresholding for different classes in SSL algorithms, and achieves remarkable performance improvement on more than twenty imbalance ratios. Specifically, we explicitly optimize the number of pseudo-labels for each class in the SSL objective, so as to simultaneously obtain adaptive thresholds and minimize empirical risk. Moreover, the determination of the adaptive threshold can be efficiently obtained by a closed-form solution. Extensive experimental results demonstrate the effectiveness of our proposed algorithms.
Author Information
Lan-Zhe Guo (Nanjing University)
Yu-Feng Li (Nanjing University)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Poster: Class-Imbalanced Semi-Supervised Learning with Adaptive Thresholding »
Tue. Jul 19th through Wed the 20th Room Hall E #535
More from the Same Authors
-
2023 Oral: ODS: Test-Time Adaptation in the Presence of Open-World Data Shift »
Zhi Zhou · Lan-Zhe Guo · Lin-Han Jia · Dingchu Zhang · Yu-Feng Li -
2023 Oral: Bidirectional Adaptation for Robust Semi-Supervised Learning with Inconsistent Data Distributions »
Lin-Han Jia · Lan-Zhe Guo · Zhi Zhou · Jie-Jing Shao · Yuke Xiang · Yu-Feng Li -
2023 Poster: Bidirectional Adaptation for Robust Semi-Supervised Learning with Inconsistent Data Distributions »
Lin-Han Jia · Lan-Zhe Guo · Zhi Zhou · Jie-Jing Shao · Yuke Xiang · Yu-Feng Li -
2023 Poster: Identifying Useful Learnwares for Heterogeneous Label Spaces »
Lan-Zhe Guo · Zhi Zhou · Yu-Feng Li · Zhi-Hua Zhou -
2023 Poster: ODS: Test-Time Adaptation in the Presence of Open-World Data Shift »
Zhi Zhou · Lan-Zhe Guo · Lin-Han Jia · Dingchu Zhang · Yu-Feng Li -
2021 Poster: Dash: Semi-Supervised Learning with Dynamic Thresholding »
Yi Xu · Lei Shang · Jinxing Ye · Qi Qian · Yu-Feng Li · Baigui Sun · Hao Li · rong jin -
2021 Oral: Dash: Semi-Supervised Learning with Dynamic Thresholding »
Yi Xu · Lei Shang · Jinxing Ye · Qi Qian · Yu-Feng Li · Baigui Sun · Hao Li · rong jin -
2020 Poster: Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data »
Lan-Zhe Guo · Zhen-Yu Zhang · Yuan Jiang · Yu-Feng Li · Zhi-Hua Zhou