Data to 13 Oct 2026

Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions

arXiv 1812.03664 ↗First posted 10 Dec 2018cs.LG cs.CVcited by 294

Not on the map. Why?

Abstract (arXiv)

Learning with limited data is a key challenge for visual recognition. Many few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes with limited labels. This style of transfer learning is task-agnostic: the embedding function is not learned optimally discriminative with respect to the unseen classes, where discerning among them leads to the target task. In this paper, we propose a novel approach to adapt the instance embeddings to the target classification task with a set-to-set function, yielding embeddings that are task-specific and are discriminative. We empirically investigated various instantiations of such set-to-set functions and observed the Transformer is most effective -- as it naturally satisfies key properties of our desired model. We denote this model as FEAT (few-shot embedding adaptation w/ Transformer) and validate it on both the standard few-shot classification benchmark and four extended few-shot learning settings with essential use cases, i.e., cross-domain, transductive, generalized few-shot learning, and low-shot learning. It archived consistent improvements over baseline models as well as previous methods and established the new state-of-the-art results on two benchmarks.

Key facts. Cited by 294 papers in the map (data through 13 Oct 2026). First posted on arXiv 10 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 80; 2022: 70; 2023: 63; 2024: 42; 2025: 26; 2026: 13.

294 papers.

Sort:

By area:

2021Transformers in Vision: A Surveycited by 1,010
2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 187
2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
2021Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minimacited by 118
2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 116
2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
2023Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entitiescited by 112
2023Generating images of rare concepts using pre-trained diffusion modelscited by 79
2024SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusioncited by 75
2021Relational Embedding for Few-Shot Classificationcited by 74
2021Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learningcited by 72

38 more

2022Where in the World is this Image? Transformer-based Geo-localization in the Wildcited by 58
2022HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learningcited by 55
2021ISTR: End-to-End Instance Segmentation with Transformerscited by 52
2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
2022Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classificationcited by 50
2022Hybrid Relation Guided Set Matching for Few-shot Action Recognitioncited by 49
2021Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Datacited by 48
2023STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tablescited by 48
2023A Closer Look at Few-shot Classification Againcited by 46
2021Orthogonal Projection Losscited by 44
2023Norm-guided latent space exploration for text-to-image generationcited by 43
2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
2023CLIP-guided Prototype Modulating for Few-shot Action Recognitioncited by 41
2022Generating Representative Samples for Few-Shot Classificationcited by 39
2022Rethinking Generalization in Few-Shot Classificationcited by 36
2022Compound Prototype Matching for Few-shot Action Recognitioncited by 35
2021Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgettingcited by 33
2021Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifiercited by 32
2022Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?cited by 31
2022Few-Shot Classification with Contrastive Learningcited by 31
2023Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinementcited by 30
2021Few-shot Open-set Recognition by Transformation Consistencycited by 29
2021Few-shot Action Recognition with Prototype-centered Attentive Learningcited by 28
2022Realistic Evaluation of Transductive Few-Shot Learningcited by 27
2021Binocular Mutual Learning for Improving Few-shot Classificationcited by 26
2023Semi-Supervised Domain Adaptation with Source Label Adaptationcited by 26
2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
2024MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognitioncited by 25
2021Procrustean Training for Imbalanced Deep Learningcited by 24
2022HyperShot: Few-Shot Learning by Kernel HyperNetworkscited by 24
2023Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Modelscited by 24
2023Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentationcited by 24
2023Boosting Few-shot Action Recognition with Graph-guided Hybrid Matchingcited by 24
2021Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developmentscited by 23
2021Transductive Few-Shot Classification on the Oblique Manifoldcited by 23
2022Few-shot Learning with Noisy Labelscited by 23
2023Supervised Masked Knowledge Distillation for Few-Shot Transformerscited by 23

50 most cited of 294 All 294 (JSON)