# Cross-Domain Few-Shot Learning with Meta Fine-Tuning

arXiv: https://arxiv.org/abs/2005.10544 · HTML: https://mlsanity.com/paper/2005.10544/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2020.

## Built on by (most cited first, 8 of 8)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark](https://mlsanity.com/paper/2104.02638/) (2021)
- [Hierarchical Variational Memory for Few-shot Learning Across Domains](https://mlsanity.com/paper/2112.08181/) (2021)
- [Mask-guided Vision Transformer (MG-ViT) for Few-Shot Learning](https://mlsanity.com/paper/2205.09995/) (2022)
- [Modular Adaptation for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2104.00619/) (2021)
- [Anomaly Crossing: New Horizons for Video Anomaly Detection as Cross-domain Few-shot Learning](https://mlsanity.com/paper/2112.06320/) (2021)
- [Domain Agnostic Few-Shot Learning For Document Intelligence](https://mlsanity.com/paper/2111.00007/) (2021)
- [Dual Adversarial Alignment for Realistic Support-Query Shift Few-shot Learning](https://mlsanity.com/paper/2309.02088/) (2023)

## Abstract (arXiv)

In this paper, we tackle the new Cross-Domain Few-Shot Learning benchmark proposed by the CVPR 2020 Challenge. To this end, we build upon state-of-the-art methods in domain adaptation and few-shot learning to create a system that can be trained to perform both tasks. Inspired by the need to create models designed to be fine-tuned, we explore the integration of transfer-learning (fine-tuning) with meta-learning algorithms, to train a network that has specific layers that are designed to be adapted at a later fine-tuning stage. To do so, we modify the episodic training process to include a first-order MAML-based meta-learning algorithm, and use a Graph Neural Network model as the subsequent meta-learning module. We find that our proposed method helps to boost accuracy significantly, especially when combined with data augmentation. In our final results, we combine the novel method with the baseline method in a simple ensemble, and achieve an average accuracy of 73.78% on the benchmark. This is a 6.51% improvement over existing benchmarks that were trained solely on miniImagenet.