# Meta-Learning for Classifier Selection in Image Datasets: A Feature-Driven Framework for Accuracy Prediction

arXiv: https://arxiv.org/abs/2609.11041 · HTML: https://mlsanity.com/paper/2609.11041/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 57 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Builds on (most cited first, 13 of 13)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [How Complex is your classification problem? A survey on measuring classification complexity](https://mlsanity.com/paper/1808.03591/) (2018)
- [Adaptive Huber Regression](https://mlsanity.com/paper/1706.06991/) (2017)
- [Self-Sampling Meta SAM: Enhancing Few-shot Medical Image Segmentation with Meta-Learning](https://mlsanity.com/paper/2308.16466/) (2023)
- [Spectral Metric for Dataset Complexity Assessment](https://mlsanity.com/paper/1905.07299/) (2019)
- [Measures of Complexity for Large Scale Image Datasets](https://mlsanity.com/paper/2008.04431/) (2020)
- [Meta-Learning Initializations for Image Segmentation](https://mlsanity.com/paper/1912.06290/) (2019)
- [MetaDelta: A Meta-Learning System for Few-shot Image Classification](https://mlsanity.com/paper/2102.10744/) (2021)
- [Data Quality Measures and Efficient Evaluation Algorithms for Large-Scale High-Dimensional Data](https://mlsanity.com/paper/2101.01441/) (2021)
- [Data Separability for Neural Network Classifiers and the Development of a Separability Index](https://mlsanity.com/paper/2005.13120/) (2020)
- [Evaluating Meta-Feature Selection for the Algorithm Recommendation Problem](https://mlsanity.com/paper/2106.03954/) (2021)

## Abstract (arXiv)

No Free Lunch theorem implies that any performance gains achieved by a classifier on a particular image distribution are necessarily offset by a loss of performance over the set of all possible problems; thus, no single model is universally optimal. Selecting the most suitable classifier for image datasets is a critical yet challenging task due to the intrinsic complexity and diversity of images. This paper proposes a meta-learning framework that leverages a comprehensive set of meta-features capturing dataset complexity to predict classifier performance without exhaustive training. By extracting and selecting features using methods such as autoencoders, pre-trained networks, and dimensionality reduction techniques, we train regression models to efficiently estimate classifier accuracies. Additionally, clustering techniques are employed to group classifiers with similar performance patterns, simplifying the recommendation process. The datasets used span a wide range of concepts, including nature, animals, numbers, motorcycles, medical images, and human bodies, to ensure broad generalization. Evaluated on 56 diverse image datasets, our approach achieves an average ranking prediction accuracy exceeding 86%, demonstrating its effectiveness in guiding model selection. This scalable and interpretable framework provides a practical solution to improve classification performance while reducing computational costs.