Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Alignment-based few-shot metric learning

Learns dynamic alignment, affiliation and task-tailored embeddings between support and query samples.

38 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2020–2026) · an approach in Zero-/few-shot and meta-learning, keyword cluster “fsl · shot classification · support”

State History Benchmarks Tried Checklist Preprints Who Export

How it got here

Most cited paper of each year

• 2020 · Adversarial Feature Hallucination Networks for Few-Shot Learning (CVPR 2020 · 320 citations)
• 2021 · Learning a Few-shot Embedding Model with Contrastive Learning (AAAI 2021 · 182 citations)
• 2022 · Learning To Affiliate: Mutual Centralized Learning for Few-Shot Classification (CVPR 2022 · 107 citations)
• 2023 · Transductive Few-Shot Learning With Prototype-Based Label Propagation by Iterative Graph Refinement (CVPR 2023 · 77 citations)
• 2024 · Strong Baselines for Parameter-Efficient Few-Shot Fine-Tuning (AAAI 2024 · 26 citations)
• 2025 · FSL-Rectifier: Rectify Outliers in Few-Shot Learning via Test-Time Augmentation (AAAI 2025 · 0 citations)
• 2026 · MPA: Multimodal Prototype Augmentation for Few-Shot Learning (AAAI 2026 · 0 citations)

Earliest papers here

• Adversarial Feature Hallucination Networks for Few-Shot Learning (CVPR 2020 · 320 citations)
• Boosting Few-Shot Learning With Adaptive Margin Loss (CVPR 2020 · 202 citations)
• Instance Credibility Inference for Few-Shot Learning (CVPR 2020 · 201 citations)

Benchmark records

The best number each year that beat every earlier one, among papers of this approach reporting their own method. Numbers are extracted by AI from each paper's text; check the paper before citing.

What has been tried

31 papers here report 367 measured changes (a component added, removed or swapped, compared with a baseline): helped 74%, no clear effect 4%, hurt 19%, mixed 4%. Papers mostly publish changes that helped, so "helped" is over-represented.

Ablations in recent papers

What reviewers will expect

Datasets and baselines named in the 14 papers of this approach from 2024–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.

Recent preprints

Who publishes on it

Institutions on the most papers of this approach since 2023 (of 22 papers; from OpenAlex and the papers' affiliations).

• Shanghai Jiao Tong University · 3 papers
• Zhejiang University · 2 papers
• University of Science and Technology of China · 2 papers
• Beihang University · 2 papers
• China University of Petroleum (East China) · 2 papers
• Zhejiang Lab · 2 papers

Use it

Download BibTeX of 30 key papersOpen the topic in the interactive map

Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.

Related approaches

Same keyword cluster

• Embedding adaptation for few-shot classification (71 papers)
• Fine-tuning strategies for few-shot (67 papers)
• Fine-grained and cross-domain few-shot baselines (59 papers)

Elsewhere in the topic

• Generative feature synthesis for zero-shot (117 papers)
• Zero-shot robustness and transfer (101 papers)
• Robust fine-tuning of zero-shot models (92 papers)
• Transductive and semantic-dictionary zero-shot (90 papers)
• Meta-augmentation and meta-objectives (60 papers)
• Meta-learning analysis and benchmarks (50 papers)
• Normalization and unsupervised meta-learning (39 papers)

Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).