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

Embedding adaptation for few-shot classification

Adapts feature embeddings with set functions and feature-wise transforms, including cross-domain settings.

71 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2017–2026) · an approach in Zero-/few-shot and meta-learning, keyword cluster “fsl · shot classification · support”

State History Benchmarks Tried Baselines Checklist Preprints Who Export

How it got here

Most cited paper of each year

• 2017 · Prototypical Networks for Few-shot Learning (NeurIPS 2017 · 5,178 citations)
• 2018 · Dynamic Few-Shot Visual Learning Without Forgetting (CVPR 2018 · 1,151 citations)
• 2019 · Revisiting Local Descriptor Based Image-To-Class Measure for Few-Shot Learning (CVPR 2019 · 674 citations)
• 2020 · Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions (CVPR 2020 · 776 citations)
• 2021 · Few-Shot Classification With Feature Map Reconstruction Networks (CVPR 2021 · 358 citations)
• 2022 · Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification (CVPR 2022 · 298 citations)
• 2023 · Glocal Energy-Based Learning for Few-Shot Open-Set Recognition (CVPR 2023 · 44 citations)
• 2024 · Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning (CVPR 2024 · 18 citations)
• 2025 · Multi-Label Few-Shot Image Classification via Pairwise Feature Augmentation and Flexible Prompt Learning (AAAI 2025 · 2 citations)
• 2026 · Exploiting Low-Dimensional Manifold of Features for Few-shot Whole Slide Image Classification (ICLR 2026 · 0 citations)

Earliest papers here

• Prototypical Networks for Few-shot Learning (NeurIPS 2017 · 5,178 citations)
• Dynamic Few-Shot Visual Learning Without Forgetting (CVPR 2018 · 1,151 citations)
• Meta-Learning for Semi-Supervised Few-Shot Classification (ICLR 2018 · 726 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

68 papers here report 778 measured changes (a component added, removed or swapped, compared with a baseline): helped 71%, no clear effect 8%, hurt 16%, mixed 5%. Papers mostly publish changes that helped, so "helped" is over-represented.

Ablations in recent papers

Baseline numbers that disagree

The same baseline on the same benchmark and metric, reported more than 5% apart by different papers here. Training budgets, data splits and reimplementations differ, so state which number you compare with.

What reviewers will expect

Datasets and baselines named in the 10 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 20 papers; from OpenAlex and the papers' affiliations).

• Peking University · 2 papers
• Dalian University of Technology · 2 papers
• Pennsylvania State University · 2 papers
• University of Melbourne · 2 papers
• University of Electronic Science and Technology of China · 2 papers
• Shanghai Jiao Tong University · 2 papers

Use it

Download BibTeX of 32 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

• Fine-tuning strategies for few-shot (67 papers)
• Fine-grained and cross-domain few-shot baselines (59 papers)
• Alignment-based few-shot metric learning (38 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).