Region based Ensemble Learning Network for Fine-grained Classification

TL;DR

This paper introduces a novel region-based ensemble learning network that combines object detection and ensemble classification to improve fine-grained image recognition, demonstrating effectiveness on multiple datasets.

Contribution

It presents a new framework integrating region detection with ensemble classification for enhanced fine-grained recognition performance.

Findings

Effective on CUB-2011 dataset

Extended to remote scene recognition

Proves the efficiency of the method

Abstract

As an important research topic in computer vision, fine-grained classification which aims to recognition subordinate-level categories has attracted significant attention. We propose a novel region based ensemble learning network for fine-grained classification. Our approach contains a detection module and a module for classification. The detection module is based on the faster R-CNN framework to locate the semantic regions of the object. The classification module using an ensemble learning method, which trains a set of sub-classifiers for different semantic regions and combines them together to get a stronger classifier. In the evaluation, we implement experiments on the CUB-2011 dataset and the result of experiments proves our method s efficient for fine-grained classification. We also extend our approach to remote scene recognition and evaluate it on the NWPU-RESISC45 dataset.