Explainability of artificial intelligence methods, applications and challenges: A comprehensive survey

W Ding, M Abdel-Basset, H Hawash, AM Ali - Information Sciences, 2022 - Elsevier
The continuous advancement of Artificial Intelligence (AI) has been revolutionizing the
strategy of decision-making in different life domains. Regardless of this achievement, AI …

Interpretability research of deep learning: A literature survey

B Xua, G Yang - Information Fusion, 2024 - Elsevier
Deep learning (DL) has been widely used in various fields. However, its black-box nature
limits people's understanding and trust in its decision-making process. Therefore, it becomes …

[HTML][HTML] Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence

S Ali, T Abuhmed, S El-Sappagh, K Muhammad… - Information fusion, 2023 - Elsevier
Artificial intelligence (AI) is currently being utilized in a wide range of sophisticated
applications, but the outcomes of many AI models are challenging to comprehend and trust …

Jcs: An explainable covid-19 diagnosis system by joint classification and segmentation

YH Wu, SH Gao, J Mei, J Xu, DP Fan… - … on Image Processing, 2021 - ieeexplore.ieee.org
Recently, the coronavirus disease 2019 (COVID-19) has caused a pandemic disease in
over 200 countries, influencing billions of humans. To control the infection, identifying and …

C-cam: Causal cam for weakly supervised semantic segmentation on medical image

Z Chen, Z Tian, J Zhu, C Li… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Recently, many excellent weakly supervised semantic segmentation (WSSS) works are
proposed based on class activation map** (CAM). However, there are few works that …

Expansion and shrinkage of localization for weakly-supervised semantic segmentation

J Li, Z Jie, X Wang, X Wei, L Ma - Advances in Neural …, 2022 - proceedings.neurips.cc
Generating precise class-aware pseudo ground-truths, aka, class activation maps (CAMs), is
essential for Weakly-Supervised Semantic Segmentation. The original CAM method usually …

Extracting class activation maps from non-discriminative features as well

Z Chen, Q Sun - Proceedings of the IEEE/CVF conference …, 2023 - openaccess.thecvf.com
Extracting class activation maps (CAM) from a classification model often results in poor
coverage on foreground objects, ie, only the discriminative region (eg, the" head" of" sheep") …

[HTML][HTML] Quod erat demonstrandum?-Towards a typology of the concept of explanation for the design of explainable AI

F Cabitza, A Campagner, G Malgieri, C Natali… - Expert systems with …, 2023 - Elsevier
In this paper, we present a fundamental framework for defining different types of
explanations of AI systems and the criteria for evaluating their quality. Starting from a …

Towards better understanding attribution methods

S Rao, M Böhle, B Schiele - Proceedings of the IEEE/CVF …, 2022 - openaccess.thecvf.com
Deep neural networks are very successful on many vision tasks, but hard to interpret due to
their black box nature. To overcome this, various post-hoc attribution methods have been …

Endoscopic image classification based on explainable deep learning

D Mukhtorov, M Rakhmonova, S Muksimova, YI Cho - Sensors, 2023 - mdpi.com
Deep learning has achieved remarkably positive results and impacts on medical diagnostics
in recent years. Due to its use in several proposals, deep learning has reached sufficient …