# Predictive Ensemble Learning with Application to Scene Text Detection

## TL;DR

This paper introduces Predictive Ensemble Learning (PEL), a novel method that predicts the best model for each test example to improve scene text detection performance, transforming ensemble learning into a classification problem.

## Contribution

The paper proposes PEL, a new ensemble approach that predicts the optimal model for each instance, addressing challenges in combining models for complex tasks like object detection.

## Key findings

- PEL significantly outperforms individual state-of-the-art models.
- PEL surpasses traditional fusion methods like non-maximum suppression.
- Experimental results demonstrate PEL's ability to predict model performance based on query examples.

## Abstract

Deep learning based approaches have achieved significant progresses in different tasks like classification, detection, segmentation, and so on. Ensemble learning is widely known to further improve performance by combining multiple complementary models. It is easy to apply ensemble learning for classification tasks, for example, based on averaging, voting, or other methods. However, for other tasks (like object detection) where the outputs are varying in quantity and unable to be simply compared, the ensemble of multiple models become difficult. In this paper, we propose a new method called Predictive Ensemble Learning (PEL), based on powerful predictive ability of deep neural networks, to directly predict the best performing model among a pool of base models for each test example, thus transforming ensemble learning to a traditional classification task. Taking scene text detection as the application, where no suitable ensemble learning strategy exists, PEL can significantly improve the performance, compared to either individual state-of-the-art models, or the fusion of multiple models by non-maximum suppression. Experimental results show the possibility and potential of PEL in predicting different models' performance based only on a query example, which can be extended for ensemble learning in many other complex tasks.