.png){kind=icon}
返回
Understanding contributing neurons via attribution visualization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2023.126492.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Understanding contributing neuron features is crucial to explaining convolutional neural network (CNN) decisions. The attribution research provides an effective way to detect contributing neuron features and numerically assign them attribution scores. However, a method to clearly and intuitively represent the implications hidden in neuron attributions is lacking. Attribution scores show the numerical importance of contributing neurons, but the meanings implied by these numerical scores are still not available. To mitigate this gap, we propose an optimization-based visualization method named attribution visualiza-tion, which enables an intuitive understanding of neuron attributions. Our approach is distinguished from existing visualization methods by its ability to produce noise-free result, i.e., the ability to remove irrelevant regions from visualizations. We achieve this by introducing an optimizable mask into the visu-alization process and designing an objective function that simultaneously optimizes the area-constrained mask and visualization. Furthermore, we propose the fractal noise pyramid with diverse and natural fre-quency spectra as our mask perturbation technique which is key to removing unrelated noise in visual-ization. We implement several comparisons and user studies with other visual explanations to demonstrate the unique properties of our attribution visualization. We also apply our attribution visual-ization on two representative CNNs, showcasing its ability to intuitively understand contributing neuron features.& COPY; 2023 Elsevier B.V. All rights reserved.
Keyword:
Convolutional neural network
Feature visualization
Feature semantics
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
.png){kind=icon}
Engineering an Escherichia coli Autolytic System for Overexpression of a Collagen-Mimetic Peptide with Enhanced Hemostatic Activity构建一种用于增强促凝血活性的胶原蛋白模拟肽过表达的大肠杆菌自溶系统
PREAI
分享收藏分享收藏
Belief-Desire-Intention (BDI) Multi-agent System for Cloud Marketplace Negotiation基于信念-愿望-意图(BDI)的多智能体系统用于云市场谈判
PREAI
分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏
查看更多内容