# Instance Selection Mechanisms for Human-in-the-Loop Systems in Few-Shot Learning

arXiv: https://arxiv.org/abs/2207.06835 · HTML: https://mlsanity.com/paper/2207.06835/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 32 references that are in the map.
- First posted on arXiv 14 Jul 2022.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [TADAM: Task dependent adaptive metric for improved few-shot learning](https://mlsanity.com/paper/1805.10123/) (2018)
- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [Cost-Effective Active Learning for Deep Image Classification](https://mlsanity.com/paper/1701.03551/) (2017)
- [Hybrid Intelligence](https://mlsanity.com/paper/2105.00691/) (2021)
- [DEAL: Deep Evidential Active Learning for Image Classification](https://mlsanity.com/paper/2007.11344/) (2020)
- [Few-Shot Hyperspectral Image Classification With Unknown Classes Using Multitask Deep Learning](https://mlsanity.com/paper/2009.03508/) (2020)
- [Few-shot Learning for Domain-specific Fine-grained Image Classification](https://mlsanity.com/paper/1907.09647/) (2019)
- [Structured Set Matching Networks for One-Shot Part Labeling](https://mlsanity.com/paper/1712.01867/) (2017)
- [A Picture is Worth a Collaboration: Accumulating Design Knowledge for Computer-Vision-based Hybrid Intelligence Systems](https://mlsanity.com/paper/2104.11600/) (2021)

## Built on by (most cited first, 2 of 2)

- [Improving the Efficiency of Human-in-the-Loop Systems: Adding Artificial to Human Experts](https://mlsanity.com/paper/2307.03003/) (2023)
- [A Workflow-Oriented Framework for Asynchronous Human-AI Collaboration in Hybrid and Compute-Intensive HPC Environments](https://mlsanity.com/paper/2605.03743/) (2026)

## Abstract (arXiv)

Business analytics and machine learning have become essential success factors for various industries - with the downside of cost-intensive gathering and labeling of data. Few-shot learning addresses this challenge and reduces data gathering and labeling costs by learning novel classes with very few labeled data. In this paper, we design a human-in-the-loop (HITL) system for few-shot learning and analyze an extensive range of mechanisms that can be used to acquire human expert knowledge for instances that have an uncertain prediction outcome. We show that the acquisition of human expert knowledge significantly accelerates the few-shot model performance given a negligible labeling effort. We validate our findings in various experiments on a benchmark dataset in computer vision and real-world datasets. We further demonstrate the cost-effectiveness of HITL systems for few-shot learning. Overall, our work aims at supporting researchers and practitioners in effectively adapting machine learning models to novel classes at reduced costs.