Skip to Main content Skip to Navigation
Conference papers

Region Based Ensemble Learning Network for Fine-Grained Classification

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 semantic regions of the object. The classification module using an ensemble learning method, 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 is efficient for fine-grained classification. We also extend our approach to remote scene recognition and evaluate it on the NWPU-RESISC45 dataset.
Complete list of metadatas

https://hal-utt.archives-ouvertes.fr/hal-02359080
Contributor : Jean-Baptiste Vu Van <>
Submitted on : Tuesday, November 12, 2019 - 11:57:40 AM
Last modification on : Friday, July 17, 2020 - 8:32:02 PM

Links full text

Identifiers

Collections

Citation

Weikuang Li, Tian Wang, Chuanyun Wang, Guangcun Shan, Mengyi Zhang, et al.. Region Based Ensemble Learning Network for Fine-Grained Classification. 2018 Chinese Automation Congress (CAC), Nov 2018, Xi'an, China. pp.4173-4177, ⟨10.1109/CAC.2018.8623687⟩. ⟨hal-02359080⟩

Share

Metrics

Record views

64