Neural inference search for multiloss segmentation models

Slade, S., Zhang, L., Huang, H., Asadi, H., Lim, C. P., Yu, Y., Zhao, D. , Lin, H. and Gao, R. (2023) Neural inference search for multiloss segmentation models. IEEE Transactions on Neural Networks and Learning Systems, (doi: 10.1109/TNNLS.2023.3282799) (PMID:37327096) (Early Online Publication)

Abstract

Semantic segmentation is vital for many emerging surveillance applications, but current models cannot be relied upon to meet the required tolerance, particularly in complex tasks that involve multiple classes and varied environments. To improve performance, we propose a novel algorithm, neural inference search (NIS), for hyperparameter optimization pertaining to established deep learning segmentation models in conjunction with a new multiloss function. It incorporates three novel search behaviors, i.e., Maximized Standard Deviation Velocity Prediction, Local Best Velocity Prediction, and n -dimensional Whirlpool Search. The first two behaviors are exploratory, leveraging long short-term memory (LSTM)-convolutional neural network (CNN)-based velocity predictions, while the third employs n -dimensional matrix rotation for local exploitation. A scheduling mechanism is also introduced in NIS to manage the contributions of these three novel search behaviors in stages. NIS optimizes learning and multiloss parameters simultaneously. Compared with state-of-the-art segmentation methods and those optimized with other well-known search algorithms, NIS-optimized models show significant improvements across multiple performance metrics on five segmentation datasets. NIS also reliably yields better solutions as compared with a variety of search methods for solving numerical benchmark functions.

• Item Type: Articles
• Additional Information: This work was supported in part by the European Regional Development Fund (ERDF); in part by RPPTV Ltd., through the Joint Funding of a Ph.D. Studentship via the Intensive Industrial Innovation Program North East (IIIPNE) under Grant 25R17P01847; and in part by Innovate U.K. Smart Grants.
• Status: Early Online Publication
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Zhao, Dr Dezong
• Authors: Slade, S., Zhang, L., Huang, H., Asadi, H., Lim, C. P., Yu, Y., Zhao, D., Lin, H., and Gao, R.
• College/School: College of Science and Engineering > School of Engineering > Autonomous Systems and Connectivity
• Journal Name: IEEE Transactions on Neural Networks and Learning Systems
• Publisher: IEEE
• ISSN: 2162-237X
• ISSN (Online): 2162-2388
• Published Online: 16 June 2023
• Copyright Holders: Copyright © 2023 IEEE
• First Published: First published in IEEE Transactions on Neural Networks and Learning Systems 2023
• Publisher Policy: Reproduced in accordance with the publisher copyright policy