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

arXiv: https://arxiv.org/abs/1812.03664 · HTML: https://mlsanity.com/paper/1812.03664/

## Key facts

- Cited by 294 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2018.

## Built on by (most cited first, 30 of 294)

- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)
- [Few-Shot Incremental Learning with Continually Evolved Classifiers](https://mlsanity.com/paper/2104.03047/) (2021)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias](https://mlsanity.com/paper/2101.07296/) (2021)
- [Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima](https://mlsanity.com/paper/2111.01549/) (2021)
- [Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer](https://mlsanity.com/paper/2108.03032/) (2021)
- [Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities](https://mlsanity.com/paper/2302.11154/) (2023)
- [Generating images of rare concepts using pre-trained diffusion models](https://mlsanity.com/paper/2304.14530/) (2023)
- [SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion](https://mlsanity.com/paper/2404.14197/) (2024)
- [Relational Embedding for Few-Shot Classification](https://mlsanity.com/paper/2108.09666/) (2021)
- [Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning](https://mlsanity.com/paper/2102.03983/) (2021)
- [Where in the World is this Image? Transformer-based Geo-localization in the Wild](https://mlsanity.com/paper/2204.13861/) (2022)
- [HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2201.04182/) (2022)
- [ISTR: End-to-End Instance Segmentation with Transformers](https://mlsanity.com/paper/2105.00637/) (2021)
- [Rectifying the Shortcut Learning of Background for Few-Shot Learning](https://mlsanity.com/paper/2107.07746/) (2021)
- [Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification](https://mlsanity.com/paper/2204.04567/) (2022)
- [Hybrid Relation Guided Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2204.13423/) (2022)
- [STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables](https://mlsanity.com/paper/2303.00918/) (2023)
- [Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data](https://mlsanity.com/paper/2107.11978/) (2021)
- [A Closer Look at Few-shot Classification Again](https://mlsanity.com/paper/2301.12246/) (2023)
- [Orthogonal Projection Loss](https://mlsanity.com/paper/2103.14021/) (2021)
- [Norm-guided latent space exploration for text-to-image generation](https://mlsanity.com/paper/2306.08687/) (2023)
- [Learning Dynamic Alignment via Meta-filter for Few-shot Learning](https://mlsanity.com/paper/2103.13582/) (2021)
- [CLIP-guided Prototype Modulating for Few-shot Action Recognition](https://mlsanity.com/paper/2303.02982/) (2023)
- [Generating Representative Samples for Few-Shot Classification](https://mlsanity.com/paper/2205.02918/) (2022)
- [Rethinking Generalization in Few-Shot Classification](https://mlsanity.com/paper/2206.07267/) (2022)
- [Compound Prototype Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2207.05515/) (2022)
- [Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting](https://mlsanity.com/paper/2108.08165/) (2021)
- [Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier](https://mlsanity.com/paper/2101.00562/) (2021)

## 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.