Koch T, Rieß C, Köhler T (2023)
Publication Language: English
Publication Type: Conference contribution, Conference Contribution
Publication year: 2023
Publisher: IEEE
Series: Computer Vision Workshops
Pages Range: 4388-4398
Conference Proceedings Title: 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
ISBN: 979-8-3503-0744-3
URI: https://faui1-files.cs.fau.de/public/publications/mmsec/2023-Koch-ICCVW.pdf
DOI: 10.1109/ICCVW60793.2023.00473
Handling entirely unknown data is a challenge for any deployed classifier. Classification models are typically trained on a static pre-defined dataset and are kept in the dark for the open unassigned feature space. As a result, they struggle to deal with out-of-distribution data during inference. Addressing this task on the class-level is termed open-set recognition (OSR). However, most OSR methods are inherently limited, as they train closed-set classifiers and only adapt the downstream predictions to OSR.
This work presents LORD, a framework to Leverage Open-set Recognition by exploiting unknown Data. LORD explicitly models open space during classifier training and provides a systematic evaluation for such approaches. We identify three model-agnostic training strategies that exploit background data and applied them to well-established classifiers. Due to LORD's extensive evaluation protocol, we consistently demonstrate improved recognition of unknown data. The benchmarks facilitate in-depth analysis across various requirement levels. To mitigate dependency on extensive and costly background datasets, we explore mixup as an off-the-shelf data generation technique. Our experiments highlight mixup's effectiveness as a substitute for background datasets. Lightweight constraints on mixup synthesis further improve OSR performance.
APA:
Koch, T., Rieß, C., & Köhler, T. (2023). LORD: Leveraging Open-Set Recognition with Unknown Data. In 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) (pp. 4388-4398). Paris, FR: IEEE.
MLA:
Koch, Tobias, Christian Rieß, and Thomas Köhler. "LORD: Leveraging Open-Set Recognition with Unknown Data." Proceedings of the International Conference on Computer Vision Workshop (ICCVW), Paris IEEE, 2023. 4388-4398.
BibTeX: Download