OISE: Optimized Input Sampling Explanation with a Saliency Map Based on the Black-Box Model
With the development of artificial intelligence technology, machine learning models are becoming more complex and accurate. However, the explainability of the models is decreasing, and much of the decision process is still unclear and difficult to explain to users. Therefore, we now often use Explai...
Main Authors: | Zhan Wang, Inwhee Joe |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-05-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/10/5886 |
Similar Items
-
Explainable AI Evaluation: A Top-Down Approach for Selecting Optimal Explanations for Black Box Models
by: SeyedehRoksana Mirzaei, et al.
Published: (2023-12-01) -
GSM-HM: Generation of Saliency Maps for Black-Box Object Detection Model Based on Hierarchical Masking
by: Yicheng Yan, et al.
Published: (2022-01-01) -
Visual explanations with detailed spatial information for remote sensing image classification via channel saliency
by: Xianpeng Guo, et al.
Published: (2023-04-01) -
Explaining any black box model using real data
by: Anton Björklund, et al.
Published: (2023-08-01) -
What about the Latent Space? The Need for Latent Feature Saliency Detection in Deep Time Series Classification
by: Maresa Schröder, et al.
Published: (2023-05-01)