Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2312.15702 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913296430399488 |
|---|---|
| author | Ma, Chengcheng Elezi, Ismail Deng, Jiankang Dong, Weiming Xu, Changsheng |
| author_facet | Ma, Chengcheng Elezi, Ismail Deng, Jiankang Dong, Weiming Xu, Changsheng |
| contents | We address the challenging problem of Long-Tailed Semi-Supervised Learning (LTSSL) where labeled data exhibit imbalanced class distribution and unlabeled data follow an unknown distribution. Unlike in balanced SSL, the generated pseudo-labels are skewed towards head classes, intensifying the training bias. Such a phenomenon is even amplified as more unlabeled data will be mislabeled as head classes when the class distribution of labeled and unlabeled datasets are mismatched. To solve this problem, we propose a novel method named ComPlementary Experts (CPE). Specifically, we train multiple experts to model various class distributions, each of them yielding high-quality pseudo-labels within one form of class distribution. Besides, we introduce Classwise Batch Normalization for CPE to avoid performance degradation caused by feature distribution mismatch between head and non-head classes. CPE achieves state-of-the-art performances on CIFAR-10-LT, CIFAR-100-LT, and STL-10-LT dataset benchmarks. For instance, on CIFAR-10-LT, CPE improves test accuracy by over 2.22% compared to baselines. Code is available at https://github.com/machengcheng2016/CPE-LTSSL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_15702 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Three Heads Are Better Than One: Complementary Experts for Long-Tailed Semi-supervised Learning Ma, Chengcheng Elezi, Ismail Deng, Jiankang Dong, Weiming Xu, Changsheng Computer Vision and Pattern Recognition We address the challenging problem of Long-Tailed Semi-Supervised Learning (LTSSL) where labeled data exhibit imbalanced class distribution and unlabeled data follow an unknown distribution. Unlike in balanced SSL, the generated pseudo-labels are skewed towards head classes, intensifying the training bias. Such a phenomenon is even amplified as more unlabeled data will be mislabeled as head classes when the class distribution of labeled and unlabeled datasets are mismatched. To solve this problem, we propose a novel method named ComPlementary Experts (CPE). Specifically, we train multiple experts to model various class distributions, each of them yielding high-quality pseudo-labels within one form of class distribution. Besides, we introduce Classwise Batch Normalization for CPE to avoid performance degradation caused by feature distribution mismatch between head and non-head classes. CPE achieves state-of-the-art performances on CIFAR-10-LT, CIFAR-100-LT, and STL-10-LT dataset benchmarks. For instance, on CIFAR-10-LT, CPE improves test accuracy by over 2.22% compared to baselines. Code is available at https://github.com/machengcheng2016/CPE-LTSSL. |
| title | Three Heads Are Better Than One: Complementary Experts for Long-Tailed Semi-supervised Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.15702 |