.png){kind=icon}
返回
Recursive Visual Explanations Mediation Scheme Based on DropAttention Model With Multiple Episodes Pool
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2023.3235332.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In some DL applications such as remote sensing, it is hard to obtain the high task performance (e.g. accuracy) using the DL model on image analysis due to the low resolution characteristics of the imagery. Accordingly, several studies attempted to provide visual explanations or apply the attention mechanism to enhance the reliability on the image analysis. However, there still remains structural complexity on obtaining a sophisticated visual explanation with such existing methods: 1) which layer will the visual explanation be extracted from, and 2) which layers the attention modules will be applied to. 3) Subsequently, in order to observe the aspects of visual explanations on such diverse episodes of applying attention modules individually, training cost inefficiency inevitably arises as it requires training the multiple models one by one in the conventional methods. In order to solve the problems, we propose a new scheme of mediating the visual explanations in a pixel-level recursively. Specifically, we propose DropAtt that generates multiple episodes pool by training only a single network once as an amortized model, which also shows stability on task performance regardless of layer-wise attention policy. From the multiple episodes pool generated by DropAtt, by quantitatively evaluating the explainability of each visual explanation and expanding the parts of explanations with high explainability recursively, our visual explanations mediation scheme attempts to adjust how much to reflect each episodic layer-wise explanation for enforcing a dominant explainability of each candidate. On the empirical evaluation, our methods show their feasibility on enhancing the visual explainability by reducing average drop about 17% and enhancing the rate of increase in confidence 3%.
Keyword:
Visualization
Task analysis
Training data
Predictive models
Feature extraction
Computational modeling
Location awareness
Explainable AI (XAI)
attention
class activation map (CAM)
amortized model
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
暂无机构信息
引用论文
Parallel Decentralized Damage Detection of a Structure with Subsets of Parameters.png)
AIAA Journal
AIAA JournalIF0
PREAI
分享收藏Intercellular Adhesion Molecule 1 (ICAM-1) Gene Variant is Associated with Coronary Artery Calcification Independent of Soluble ICAM-1 Levels细胞间粘附分子1 (ICAM-1) 基因变异与冠状动脉钙化相关，与可溶性ICAM-1水平无关
PREAI
分享收藏
查看更多内容