FATE: A Prompt-Tuning-Based Semi-Supervised Learning Framework for Extremely Limited Labeled Data
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909578922295296 |
|---|---|
| author | Liu, Hezhao Lu, Yang Li, Mengke Zhang, Yiqun Gowda, Shreyank N Gong, Chen Wang, Hanzi |
| author_facet | Liu, Hezhao Lu, Yang Li, Mengke Zhang, Yiqun Gowda, Shreyank N Gong, Chen Wang, Hanzi |
| contents | Semi-supervised learning (SSL) has achieved significant progress by leveraging both labeled data and unlabeled data. Existing SSL methods overlook a common real-world scenario when labeled data is extremely scarce, potentially as limited as a single labeled sample in the dataset. General SSL approaches struggle to train effectively from scratch under such constraints, while methods utilizing pre-trained models often fail to find an optimal balance between leveraging limited labeled data and abundant unlabeled data. To address this challenge, we propose Firstly Adapt, Then catEgorize (FATE), a novel SSL framework tailored for scenarios with extremely limited labeled data. At its core, the two-stage prompt tuning paradigm FATE exploits unlabeled data to compensate for scarce supervision signals, then transfers to downstream tasks. Concretely, FATE first adapts a pre-trained model to the feature distribution of downstream data using volumes of unlabeled samples in an unsupervised manner. It then applies an SSL method specifically designed for pre-trained models to complete the final classification task. FATE is designed to be compatible with both vision and vision-language pre-trained models. Extensive experiments demonstrate that FATE effectively mitigates challenges arising from the scarcity of labeled samples in SSL, achieving an average performance improvement of 33.74% across seven benchmarks compared to state-of-the-art SSL methods. Code is available at https://anonymous.4open.science/r/Semi-supervised-learning-BA72. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09828 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FATE: A Prompt-Tuning-Based Semi-Supervised Learning Framework for Extremely Limited Labeled Data Liu, Hezhao Lu, Yang Li, Mengke Zhang, Yiqun Gowda, Shreyank N Gong, Chen Wang, Hanzi Computer Vision and Pattern Recognition Machine Learning Semi-supervised learning (SSL) has achieved significant progress by leveraging both labeled data and unlabeled data. Existing SSL methods overlook a common real-world scenario when labeled data is extremely scarce, potentially as limited as a single labeled sample in the dataset. General SSL approaches struggle to train effectively from scratch under such constraints, while methods utilizing pre-trained models often fail to find an optimal balance between leveraging limited labeled data and abundant unlabeled data. To address this challenge, we propose Firstly Adapt, Then catEgorize (FATE), a novel SSL framework tailored for scenarios with extremely limited labeled data. At its core, the two-stage prompt tuning paradigm FATE exploits unlabeled data to compensate for scarce supervision signals, then transfers to downstream tasks. Concretely, FATE first adapts a pre-trained model to the feature distribution of downstream data using volumes of unlabeled samples in an unsupervised manner. It then applies an SSL method specifically designed for pre-trained models to complete the final classification task. FATE is designed to be compatible with both vision and vision-language pre-trained models. Extensive experiments demonstrate that FATE effectively mitigates challenges arising from the scarcity of labeled samples in SSL, achieving an average performance improvement of 33.74% across seven benchmarks compared to state-of-the-art SSL methods. Code is available at https://anonymous.4open.science/r/Semi-supervised-learning-BA72. |
| title | FATE: A Prompt-Tuning-Based Semi-Supervised Learning Framework for Extremely Limited Labeled Data |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2504.09828 |