Autor: |
Wozniak, Anne-Laure, Segura Rueda, Sergio, Mazo, Raúl, Leroy, Sarah |
Přispěvatelé: |
Universidad de Sevilla. Departamento de Lenguajes y Sistemas Informáticos, Universidad de Sevilla. TIC-205: Ingeniería del Software Aplicada, French National Agency of Research and Technology (ANRT), Junta de Andalucía, Ministerio de Ciencia e Innovación (MICIN). España |
Rok vydání: |
2022 |
Předmět: |
|
Zdroj: |
Proceedings of the 1st Workshop on Software Engineering for Responsible AI. |
DOI: |
10.1145/3526073.3527592 |
Popis: |
artifi-cial intelligence (AI), methods have been proposed and evaluated in academia to assess the reliability of these systems. In the context of computer vision, some approaches use the generation of images altered by common perturbations and realistic transformations to assess the robustness of systems. To better understand the strengths and limitations of these approaches, we report the results obtained on an industrial case of a road object detection system. By compar-ing these results with those of reference models, we identify areas for improvement regarding the robustness of the system and the metrics used for this evaluation. CCS CONCEP French National Agency of Research and Technology (ANRT) CIFRE N°2020/0754 Junta de Andalucía P18-FR-2895 (EKIPMENT-PLUS) Junta de Andalucía US-1264651 (APOLO) Ministerio de Ciencia e Innovación RTI2018-101204-B-C21 (HORATIO) |
Databáze: |
OpenAIRE |
Externí odkaz: |
|