English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Although 3D point cloud classification neural network models have been widelyused, the in-depth interpretation of the activation of the neurons and layersis still a challenge. We propose a novel approach, named Relevance Flow, tointerpret the hidden semantics of 3D point cloud classification neuralnetworks. It delivers the class Relevance to the activated neurons in theintermediate layers in a back-propagation manner, and associates the activationof neurons with the input points to visualize the hidden semantics of eachlayer. Specially, we reveal that the 3D point cloud classification neuralnetwork has learned the plane-level and part-level hidden semantics in theintermediate layers, and utilize the normal and IoU to evaluate the consistencyof both levels' hidden semantics. Besides, by using the hidden semantics, wegenerate the adversarial attack samples to attack 3D point cloud classifiers.Experiments show that our proposed method reveals the hidden semantics of the3D point cloud classification neural network on ModelNet40 and ShapeNet, whichcan be used for the unsupervised point cloud part segmentation without labelsand attacking the 3D point cloud classifiers.

Interpreting Hidden Semantics in the Intermediate Layers of 3D Point Cloud Classification Neural Network