Paper
23 May 2023 Multi-level feature networks for out-of-distribution image detection
Xiangyang Zhao, Quansheng Dou
Author Affiliations +
Proceedings Volume 12645, International Conference on Computer, Artificial Intelligence, and Control Engineering (CAICE 2023); 126450P (2023) https://doi.org/10.1117/12.2681328
Event: International Conference on Computer, Artificial Intelligence, and Control Engineering (CAICE 2023), 2023, Hangzhou, China
Abstract
The out-of-distribution detection task is a hot problem in image processing, aiming to detect samples that have never been trained by a deep learning model, thus ensuring the safety of the model for use in real-world environments. Currently widely used out-of-distribution detection methods suffer from single-layer representation dependence and poor adaptability. In order to overcome these problems, this paper proposes a Multilevel Feature Detection Network (MFDNet), which detects different representations of different out-of-distribution examples with the help of intermediate layer features. At the same time, a grouping module is introduced in the final layer of MFDNet to help the model reduce the decision boundaries between categories and enhance the adaptability of the model. A comparison with several common out-of-distribution detection methods on the out-of-distribution evaluation datasets validates that MFDNet can effectively handle the out-of-distribution detection task.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiangyang Zhao and Quansheng Dou "Multi-level feature networks for out-of-distribution image detection", Proc. SPIE 12645, International Conference on Computer, Artificial Intelligence, and Control Engineering (CAICE 2023), 126450P (23 May 2023); https://doi.org/10.1117/12.2681328
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Education and training

Statistical modeling

Semantics

Mahalanobis distance

Network architectures

Performance modeling

Feature extraction

Back to Top