Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914040383537152 |
|---|---|
| author | Guan, Yunchuan Liu, Yu Zhou, Ke Shen, Zhiqi Hwang, Jenq-Neng Belongie, Serge Li, Lei |
| author_facet | Guan, Yunchuan Liu, Yu Zhou, Ke Shen, Zhiqi Hwang, Jenq-Neng Belongie, Serge Li, Lei |
| contents | Meta-learning is a powerful paradigm for tackling few-shot tasks. However, recent studies indicate that models trained with the whole-class training strategy can achieve comparable performance to those trained with meta-learning in few-shot classification tasks. To demonstrate the value of meta-learning, we establish an entropy-limited supervised setting for fair comparisons. Through both theoretical analysis and experimental validation, we establish that meta-learning has a tighter generalization bound compared to whole-class training. We unravel that meta-learning is more efficient with limited entropy and is more robust to label noise and heterogeneous tasks, making it well-suited for unsupervised tasks. Based on these insights, We propose MINO, a meta-learning framework designed to enhance unsupervised performance. MINO utilizes the adaptive clustering algorithm DBSCAN with a dynamic head for unsupervised task construction and a stability-based meta-scaler for robustness against label noise. Extensive experiments confirm its effectiveness in multiple unsupervised few-shot and zero-shot tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13185 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy Guan, Yunchuan Liu, Yu Zhou, Ke Shen, Zhiqi Hwang, Jenq-Neng Belongie, Serge Li, Lei Machine Learning Artificial Intelligence Meta-learning is a powerful paradigm for tackling few-shot tasks. However, recent studies indicate that models trained with the whole-class training strategy can achieve comparable performance to those trained with meta-learning in few-shot classification tasks. To demonstrate the value of meta-learning, we establish an entropy-limited supervised setting for fair comparisons. Through both theoretical analysis and experimental validation, we establish that meta-learning has a tighter generalization bound compared to whole-class training. We unravel that meta-learning is more efficient with limited entropy and is more robust to label noise and heterogeneous tasks, making it well-suited for unsupervised tasks. Based on these insights, We propose MINO, a meta-learning framework designed to enhance unsupervised performance. MINO utilizes the adaptive clustering algorithm DBSCAN with a dynamic head for unsupervised task construction and a stability-based meta-scaler for robustness against label noise. Extensive experiments confirm its effectiveness in multiple unsupervised few-shot and zero-shot tasks. |
| title | Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2509.13185 |