# Learning from Few Samples: A Survey

arXiv: https://arxiv.org/abs/2007.15484 · HTML: https://mlsanity.com/paper/2007.15484/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2020.

## Built on by (most cited first, 23 of 23)

- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Large Language Models for Cyber Security: A Systematic Literature Review](https://mlsanity.com/paper/2405.04760/) (2024)
- [Context-enriched molecule representations improve few-shot drug discovery](https://mlsanity.com/paper/2305.09481/) (2023)
- [Few-shot Learning with Noisy Labels](https://mlsanity.com/paper/2204.05494/) (2022)
- [Neighborhood Collective Estimation for Noisy Label Identification and Correction](https://mlsanity.com/paper/2208.03207/) (2022)
- [Few-Shot Learning with Class Imbalance](https://mlsanity.com/paper/2101.02523/) (2021)
- [Parametric Scattering Networks](https://mlsanity.com/paper/2107.09539/) (2021)
- [Trans4E: Link Prediction on Scholarly Knowledge Graphs](https://mlsanity.com/paper/2107.03297/) (2021)
- [Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samples](https://mlsanity.com/paper/2210.17258/) (2022)
- [Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification](https://mlsanity.com/paper/2206.08138/) (2022)
- [Coarse-To-Fine Incremental Few-Shot Learning](https://mlsanity.com/paper/2111.14806/) (2021)
- [Revisiting Local Descriptor for Improved Few-Shot Classification](https://mlsanity.com/paper/2103.16009/) (2021)
- [Recommender systems based on graph embedding techniques: A comprehensive review](https://mlsanity.com/paper/2109.09587/) (2021)
- [Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison](https://mlsanity.com/paper/2203.14205/) (2022)
- [Generalized Zero-Shot Learning using Multimodal Variational Auto-Encoder with Semantic Concepts](https://mlsanity.com/paper/2106.14082/) (2021)
- [Show Why the Answer is Correct! Towards Explainable AI using Compositional Temporal Attention](https://mlsanity.com/paper/2105.07141/) (2021)
- [HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settings](https://mlsanity.com/paper/2312.15086/) (2023)
- [SuSana Distancia is all you need: Enforcing class separability in metric learning via two novel distance-based loss functions for few-shot image classification](https://mlsanity.com/paper/2305.09062/) (2023)
- [Subspace Adaptation Prior for Few-Shot Learning](https://mlsanity.com/paper/2310.09028/) (2023)
- [Review Neural Networks about Image Transformation Based on IGC Learning Framework with Annotated Information](https://mlsanity.com/paper/2206.10155/) (2022)
- [Delta-Patching: A Framework for Rapid Adaptation of Pre-trained Convolutional Networks without Base Performance Loss](https://mlsanity.com/paper/2303.14772/) (2023)
- [Is Meta-Learning the Right Approach for the Cold-Start Problem in Recommender Systems?](https://mlsanity.com/paper/2308.08354/) (2023)

## Abstract (arXiv)

Deep neural networks have been able to outperform humans in some cases like image recognition and image classification. However, with the emergence of various novel categories, the ability to continuously widen the learning capability of such networks from limited samples, still remains a challenge. Techniques like Meta-Learning and/or few-shot learning showed promising results, where they can learn or generalize to a novel category/task based on prior knowledge. In this paper, we perform a study of the existing few-shot meta-learning techniques in the computer vision domain based on their method and evaluation metrics. We provide a taxonomy for the techniques and categorize them as data-augmentation, embedding, optimization and semantics based learning for few-shot, one-shot and zero-shot settings. We then describe the seminal work done in each category and discuss their approach towards solving the predicament of learning from few samples. Lastly we provide a comparison of these techniques on the commonly used benchmark datasets: Omniglot, and MiniImagenet, along with a discussion towards the future direction of improving the performance of these techniques towards the final goal of outperforming humans.