English

Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning

Multimedia 2022-07-18 v3 Computation and Language Computer Vision and Pattern Recognition

Abstract

Despite achieving state-of-the-art zero-shot performance, existing vision-language models still fall short of few-shot transfer ability on domain-specific problems. Classical fine-tuning often fails to prevent highly expressive models from exploiting spurious correlations. Although model-agnostic meta-learning (MAML) presents as a natural alternative for few-shot transfer learning, the expensive computation due to implicit second-order optimization limits its use on large-scale vision-language models such as CLIP. While much literature has been devoted to exploring alternative optimization strategies, we identify another essential aspect towards effective few-shot transfer learning, task sampling, which is previously only be viewed as part of data pre-processing in MAML. To show the impact of task sampling, we propose a simple algorithm, Model-Agnostic Multitask Fine-tuning (MAMF), which differentiates classical fine-tuning only on uniformly sampling multiple tasks. Despite its simplicity, we show that MAMF consistently outperforms classical fine-tuning on five few-shot vision-language classification tasks. We further show that the effectiveness of the bi-level optimization in MAML is highly sensitive to the zero-shot performance of a task in the context of few-shot vision-language classification. The goal of this paper is to provide new insights on what makes few-shot learning work, and encourage more research into investigating better task sampling strategies.

Keywords

Cite

@article{arxiv.2203.04904,
  title  = {Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning},
  author = {Zhenhailong Wang and Hang Yu and Manling Li and Han Zhao and Heng Ji},
  journal= {arXiv preprint arXiv:2203.04904},
  year   = {2022}
}

Comments

4 pages, 4 figures, under review

R2 v1 2026-06-24T10:07:41.573Z