# Optimized Generic Feature Learning for Few-shot Classification across Domains

arXiv: https://arxiv.org/abs/2001.07926 · HTML: https://mlsanity.com/paper/2001.07926/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jan 2020.

## Built on by (most cited first, 23 of 23)

- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference](https://mlsanity.com/paper/2204.07305/) (2022)
- [Cross-domain Few-shot Learning with Task-specific Adapters](https://mlsanity.com/paper/2107.00358/) (2021)
- [Learning a Universal Template for Few-shot Dataset Generalization](https://mlsanity.com/paper/2105.07029/) (2021)
- [Universal Representation Learning from Multiple Domains for Few-shot Classification](https://mlsanity.com/paper/2103.13841/) (2021)
- [Universal Representations: A Unified Look at Multiple Task and Domain Learning](https://mlsanity.com/paper/2204.02744/) (2022)
- [Reliable Few-shot Learning under Dual Noises](https://mlsanity.com/paper/2506.16330/) (2025)
- [Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark](https://mlsanity.com/paper/2104.02638/) (2021)
- [On the Importance of Distractors for Few-Shot Classification](https://mlsanity.com/paper/2109.09883/) (2021)
- [DETA: Denoised Task Adaptation for Few-Shot Learning](https://mlsanity.com/paper/2303.06315/) (2023)
- [Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification](https://mlsanity.com/paper/2206.08138/) (2022)
- [Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Sampling](https://mlsanity.com/paper/2204.03749/) (2022)
- [Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning](https://mlsanity.com/paper/2201.05151/) (2022)
- [Neural Fine-Tuning Search for Few-Shot Learning](https://mlsanity.com/paper/2306.09295/) (2023)
- [A Survey of Historical Learning: Learning Models with Learning History](https://mlsanity.com/paper/2303.12992/) (2023)
- [Leveraging Normalization Layer in Adapters With Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2312.11260/) (2023)
- [Meta-Ensemble Parameter Learning](https://mlsanity.com/paper/2210.01973/) (2022)
- [Robust Meta-Representation Learning via Global Label Inference and Classification](https://mlsanity.com/paper/2212.11702/) (2022)
- [LAVA: Label-efficient Visual Learning and Adaptation](https://mlsanity.com/paper/2210.10317/) (2022)
- [Improving the Generalizability of Collaborative Dialogue Analysis with Multi-Feature Embeddings](https://mlsanity.com/paper/2302.04716/) (2023)
- [Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition](https://mlsanity.com/paper/2401.07061/) (2024)
- [Task-Specific Preconditioner for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2412.15483/) (2024)
- [Few-shot Classification as Multi-instance Verification: Effective Backbone-agnostic Transfer across Domains](https://mlsanity.com/paper/2507.00401/) (2025)

## Abstract (arXiv)

To learn models or features that generalize across tasks and domains is one of the grand goals of machine learning. In this paper, we propose to use cross-domain, cross-task data as validation objective for hyper-parameter optimization (HPO) to improve on this goal. Given a rich enough search space, optimization of hyper-parameters learn features that maximize validation performance and, due to the objective, generalize across tasks and domains. We demonstrate the effectiveness of this strategy on few-shot image classification within and across domains. The learned features outperform all previous few-shot and meta-learning approaches.