Loss-Based Attention for Interpreting Image-Level Prediction of Convolutional Neural Networks

Although deep neural networks have achieved great success on numerous large-scale tasks, poor interpretability is still a notorious obstacle for practical applications. In this paper, we propose a novel and general attention mechanism, loss-based attention, upon which we modify deep neural networks...

Descripción completa

Detalles Bibliográficos
Autores principales: Shi, Xiaoshuang, Xing, Fuyong, Xu, Kaidi, Chen, Pingjun, Liang, Yun, Lu, Zhiyong, Guo, Zhenhua
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2021
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9531187/
https://www.ncbi.nlm.nih.gov/pubmed/33382655
http://dx.doi.org/10.1109/TIP.2020.3046875

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9531187/
https://www.ncbi.nlm.nih.gov/pubmed/33382655
http://dx.doi.org/10.1109/TIP.2020.3046875

Ejemplares similares