Zhang, Hao and Zhou, Joey and Wang, Tianying and Tsang, Ivor and Goh, Rick Siow Mong (2020) Deep N-ary Error Correcting Output Codes. In: Mobimedia 2020, 27-28 August 2020, Cyberspace.
eai.27-8-2020.2299197.pdf - Published Version
Download (2MB) | Preview
Abstract
Ensemble learning consistently improves the performance of multi-class classification through aggregating a series of base classifiers. To this end, data-independent ensemble methods like Error Correcting Output Codes (ECOC) attract a increasing attention due to its easiness of implementation and parallelization. Specifically, traditional ECOCs and its general extension N-ary ECOC decomposes the original multi-class classification problem into a series of independent simpler classification subproblems. Unfortunately, integrating ECOCs, especially N-ary ECOC with deep neural networks, termed as deep N-ary ECOC, is not straightforward and yet fully exploited in the literature, due to high expense of training base learners. To facilitate training of N-ary ECOC with deep learning base learners, we further propose three different variants of parameter sharing architectures for deep N-ary ECOC. To verify the generalization ability of deep N-ary ECOC, we conduct experiments by varying the backbone with different deep neural networks architectures for both image and text classification task. Furthermore, extensive ablation studies on deep N-ary ECOC show its superior performance over other deep data-independent ensemble methods.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Uncontrolled Keywords: | deep n-ary ecoc ensemble learning multi-class classification |
Subjects: | Q Science > QA Mathematics > QA76 Computer software |
Depositing User: | EAI Editor I. |
Date Deposited: | 04 Feb 2021 14:19 |
Last Modified: | 04 Feb 2021 14:19 |
URI: | https://eprints.eudl.eu/id/eprint/844 |