# Diagnosing Ensemble Few-Shot Classifiers

arXiv: https://arxiv.org/abs/2206.04372 · HTML: https://mlsanity.com/paper/2206.04372/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 64 references that are in the map.
- First posted on arXiv 9 Jun 2022.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?](https://mlsanity.com/paper/2003.11539/) (2020)
- [Meta-learning with differentiable closed-form solvers](https://mlsanity.com/paper/1805.08136/) (2018)
- [Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers](https://mlsanity.com/paper/1801.06889/) (2018)
- [Diversity with Cooperation: Ensemble Methods for Few-Shot Classification](https://mlsanity.com/paper/1903.11341/) (2019)
- [Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models](https://mlsanity.com/paper/1804.09299/) (2018)
- [Do Convolutional Neural Networks Learn Class Hierarchy?](https://mlsanity.com/paper/1710.06501/) (2017)
- [ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models](https://mlsanity.com/paper/1704.01942/) (2017)
- [A Survey of Visual Analytics Techniques for Machine Learning](https://mlsanity.com/paper/2008.09632/) (2020)
- [Towards Better Analysis of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1604.07043/) (2016)
- [Understanding Hidden Memories of Recurrent Neural Networks](https://mlsanity.com/paper/1710.10777/) (2017)
- [OoDAnalyzer: Interactive Analysis of Out-of-Distribution Samples](https://mlsanity.com/paper/2002.03103/) (2020)
- [A Data Quality-Driven View of MLOps](https://mlsanity.com/paper/2102.07750/) (2021)
- [VATLD: A Visual Analytics System to Assess, Understand and Improve Traffic Light Detection](https://mlsanity.com/paper/2009.12975/) (2020)
- [Explainable Matrix -- Visualization for Global and Local Interpretability of Random Forest Classification Ensembles](https://mlsanity.com/paper/2005.04289/) (2020)
- [Dissimilarity-based Sparse Subset Selection](https://mlsanity.com/paper/1407.6810/) (2014)
- [Diagnosing Concept Drift with Visual Analytics](https://mlsanity.com/paper/2007.14372/) (2020)
- [Towards Visual Explainable Active Learning for Zero-Shot Classification](https://mlsanity.com/paper/2108.06730/) (2021)
- [Evaluation of Sampling Methods for Scatterplots](https://mlsanity.com/paper/2007.14666/) (2020)
- [Progressive Analytics: A Computation Paradigm for Exploratory Data Analysis](https://mlsanity.com/paper/1607.05162/) (2016)

## Built on by (most cited first, 13 of 13)

- [Foundation Models Meet Visualizations: Challenges and Opportunities](https://mlsanity.com/paper/2310.05771/) (2023)
- [Visual Analytics For Machine Learning: A Data Perspective Survey](https://mlsanity.com/paper/2307.07712/) (2023)
- [Human-Guided Image Generation for Expanding Small-Scale Training Image Datasets](https://mlsanity.com/paper/2412.16839/) (2024)
- [A Unified Interactive Model Evaluation for Classification, Object Detection, and Instance Segmentation in Computer Vision](https://mlsanity.com/paper/2308.05168/) (2023)
- [VideoPro: A Visual Analytics Approach for Interactive Video Programming](https://mlsanity.com/paper/2308.00401/) (2023)
- [Visual Analytics for Efficient Image Exploration and User-Guided Image Captioning](https://mlsanity.com/paper/2311.01016/) (2023)
- [Visual Analysis of Neural Architecture Spaces for Summarizing Design Principles](https://mlsanity.com/paper/2208.09665/) (2022)
- [Are We Closing the Loop Yet? Gaps in the Generalizability of VIS4ML Research](https://mlsanity.com/paper/2308.06290/) (2023)
- [A Reliable Framework for Human-in-the-Loop Anomaly Detection in Time Series](https://mlsanity.com/paper/2405.03234/) (2024)
- [VISTA: A Visual Analytics Framework to Enhance Foundation Model-Generated Data Labels](https://mlsanity.com/paper/2507.09008/) (2025)
- [RuleExplorer: A Scalable Matrix Visualization for Understanding Tree Ensemble Classifiers](https://mlsanity.com/paper/2409.03164/) (2024)
- [d-DQIVAR: Data-centric Visual Analytics and Reasoning for Data Quality Improvement](https://mlsanity.com/paper/2507.11960/) (2025)
- [Towards Explainable Quantum AI: Informing the Encoder Selection of Quantum Neural Networks via Visualization](https://mlsanity.com/paper/2512.14181/) (2025)

## Abstract (arXiv)

The base learners and labeled samples (shots) in an ensemble few-shot classifier greatly affect the model performance. When the performance is not satisfactory, it is usually difficult to understand the underlying causes and make improvements. To tackle this issue, we propose a visual analysis method, FSLDiagnotor. Given a set of base learners and a collection of samples with a few shots, we consider two problems: 1) finding a subset of base learners that well predict the sample collections; and 2) replacing the low-quality shots with more representative ones to adequately represent the sample collections. We formulate both problems as sparse subset selection and develop two selection algorithms to recommend appropriate learners and shots, respectively. A matrix visualization and a scatterplot are combined to explain the recommended learners and shots in context and facilitate users in adjusting them. Based on the adjustment, the algorithm updates the recommendation results for another round of improvement. Two case studies are conducted to demonstrate that FSLDiagnotor helps build a few-shot classifier efficiently and increases the accuracy by 12% and 21%, respectively.