Source: Proceedings. Conference titles: International Symposium on Computer-Based Medical Systems - CBMS. Unidade: ICMC
Subjects: APRENDIZADO COMPUTACIONAL, PROCESSAMENTO DE IMAGENS, RECONHECIMENTO DE IMAGEM, DIAGNÓSTICO POR COMPUTADOR
ABNT
AGUIAR, Erikson Júlio de et al. Assessing vulnerabilities of deep learning explainability in medical image analysis under adversarial settings. 2023, Anais.. Los Alamitos: IEEE, 2023. Disponível em: https://doi.org/10.1109/CBMS58004.2023.00184. Acesso em: 06 set. 2024.APA
Aguiar, E. J. de, Costa, M. V. L., Traina Junior, C., & Traina, A. J. M. (2023). Assessing vulnerabilities of deep learning explainability in medical image analysis under adversarial settings. In Proceedings. Los Alamitos: IEEE. doi:10.1109/CBMS58004.2023.00184NLM
Aguiar EJ de, Costa MVL, Traina Junior C, Traina AJM. Assessing vulnerabilities of deep learning explainability in medical image analysis under adversarial settings [Internet]. Proceedings. 2023 ;[citado 2024 set. 06 ] Available from: https://doi.org/10.1109/CBMS58004.2023.00184Vancouver
Aguiar EJ de, Costa MVL, Traina Junior C, Traina AJM. Assessing vulnerabilities of deep learning explainability in medical image analysis under adversarial settings [Internet]. Proceedings. 2023 ;[citado 2024 set. 06 ] Available from: https://doi.org/10.1109/CBMS58004.2023.00184