4.7 Article

Neural Inference Search for Multiloss Segmentation Models

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2023.3282799

关键词

Convolutional neural network (CNN); hyperparameter optimization; multiloss function; semantic segmentation

向作者/读者索取更多资源

This paper introduces a novel algorithm, neural inference search (NIS), for optimizing hyperparameters in deep learning segmentation models. NIS incorporates three new search behaviors, including maximized standard deviation velocity prediction, local best velocity prediction, and n-dimensional whirlpool search, to improve performance. Compared with state-of-the-art methods and other search algorithms, NIS-optimized models show significant improvements across multiple performance metrics on segmentation datasets.
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.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据