Improving the performance of deep learning-based classification when a sample has various appearances

ABSTRACT

In the general case, the performance of deep learning-based classification models depends on the ability of capturing features. When a sample has various appearances, the increased features may lower the performance of these models. In this case, training more models on different appearances can be a choice to improve the accuracy. In this paper, we built a new framework that generates a network of models to improve the accuracy. First, our framework built a strategy to increase the number of models to well capture the increased features. We then utilise our recursive Bayesian methods on the selected outputs of trained models, which is to reduce the similarity among these outputs for higher accuracy. The experimental results show that our framework can be a good choice to improve the performance of deep learning applications.

KEYWORDS:

• Deep learning
• various appearances
• similarity
• recursive Bayesian methods

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work has been supported by the National Natural Science Foundation of China (Grant No. 61802279, 6180021345, 61702281, 61702366) and Natural Science Foundation of Tianjin (Grant No. 18JCQNJC70300, 19JCTPJC49200, 19PTZWHZ00020, 19JCYBJC15800) and the Fundamental Research Funds for the Tianjin Universities (Grant No. 2019KJ019) and the Tianjin Science and Technology Program (Grant No. 19PTZWHZ00020)and in part by the State Key Laboratory of ASIC & System (Grant No. 2021KF014) and Tianjin Educational Commission Scientific Research Program Project (Grant No. 2020KJ112, 2018KJ215) and the fund of Beijing Polytechnic (Grant No. 2022X017-KXZ. ,