ZHANG, Qinglong; RAO, Lu; YANG, Yubin. A Novel Visual Interpretability for Deep Neural Networks by Optimizing Activation Maps with Perturbation. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 35, n. 4, p. 3377–3384, 2021. DOI: 10.1609/aaai.v35i4.16450. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/16450. Acesso em: 13 may. 2026.