.png){kind=icon}
返回
Look inside 3D point cloud deep neural network by patch-wise saliency map
.png){kind=icon}
PRE
AI
DOI：10.3233/ICA-230725.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The 3D point cloud deep neural network (3D DNN) has achieved remarkable success, but its black-box nature hinders its application in many safety-critical domains. The saliency map technique is a key method to look inside the black-box and determine where a 3D DNN focuses when recognizing a point cloud. Existing point-wise point cloud saliency methods are proposed to illustrate the point-wise saliency for a given 3D DNN. However, the above critical points are alternative and unreliable. The findings are grounded on our experimental results which show that a point becomes critical because it is responsible for representing one specific local structure. However, one local structure does not have to be represented by some specific points, conversely. As a result, discussing the saliency of the local structure (named patch-wise saliency) represented by critical points is more meaningful than discussing the saliency of some specific points. Based on the above motivations, this paper designs a black-box algorithm to generate patch-wise saliency map for point clouds. Our basic idea is to design the Mask Building-Dropping process, which adaptively matches the size of important/unimportant patches by clustering points with close saliency. Experimental results on several typical 3D DNNs show that our patch-wise saliency algorithm can provide better visual guidance, and can detect where a 3D DNN is focusing more efficiently than a point-wise saliency map. Finally, we apply our patch-wise saliency map to adversarial attacks and backdoor defenses. The results show that the improvement is significant.
Keyword:
Saliency map
point cloud
deep neural network
critical points
adversarial attack
期刊
I
IF:
5.3
论文数:
491
被引数:
735
机构
引用论文
Deep learning techniques for recommender systems based on collaborative filtering.png)
EXPERT SYSTEMS
EXPERT SYSTEMSIF2.3
PREAI
分享收藏Research on Rapid Recognition of Moving Small Targets by Robotic Arms Based on Attention Mechanisms
OAAI
OAAI分享收藏
查看更多内容