mlsanityData to 7 Oct 2026

Optimized Generic Feature Learning for Few-shot Classification across Domains

arXiv 2001.07926 ↗First posted 22 Jan 2020cs.CVcited by 23

Not on the map. Why?

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.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Jan 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 9; 2023: 5; 2024: 2; 2025: 2.

23 papers.

Sort:

  1. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  2. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
  3. 2021Cross-domain Few-shot Learning with Task-specific Adapterscited by 79
  4. 2021Learning a Universal Template for Few-shot Dataset Generalizationcited by 61
  5. 2021Universal Representation Learning from Multiple Domains for Few-shot Classificationcited by 56
  6. 2022Universal Representations: A Unified Look at Multiple Task and Domain Learningcited by 23
  7. 2021Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmarkcited by 16
  8. 2025Reliable Few-shot Learning under Dual Noisescited by 16
  9. 2021On the Importance of Distractors for Few-Shot Classificationcited by 14
  10. 2023DETA: Denoised Task Adaptation for Few-Shot Learningcited by 13
  11. 2022Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classificationcited by 10
  12. 2022Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Samplingcited by 8
11 more
  1. 2022Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learningcited by 4
  2. 2023Neural Fine-Tuning Search for Few-Shot Learningcited by 4
  3. 2023A Survey of Historical Learning: Learning Models with Learning Historycited by 3
  4. 2023Leveraging Normalization Layer in Adapters With Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learningcited by 3
  5. 2022Meta-Ensemble Parameter Learningcited by 2
  6. 2022Robust Meta-Representation Learning via Global Label Inference and Classificationcited by 2
  7. 2022LAVA: Label-efficient Visual Learning and Adaptationcited by 1
  8. 2023Improving the Generalizability of Collaborative Dialogue Analysis with Multi-Feature Embeddingscited by 1
  9. 2024Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognitioncited by 1
  10. 2024Task-Specific Preconditioner for Cross-Domain Few-Shot Learningcited by 1
  11. 2025Few-shot Classification as Multi-instance Verification: Effective Backbone-agnostic Transfer across Domainscited by 0