Point Gated Attention - Université de technologie de Troyes Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Point Gated Attention

Résumé

Self-attention networks have achieved great success in traditional language processing, and have also made great progress in image classification and object detection. When analyzing the previous work, it is found that some point cloud information is lost in their feature extraction work, so we design a network to reduce the loss when extracting features. And through the feature extraction network - Gated Attention Unit instead of Transformer, to make the extraction of point cloud features more efficient. Based on Point Transformer, a new network structure named Point Gated Attention is used to classify point clouds. The overall_acc on the dataset ModelNet40 can reach 91.4%, and the average accuracy can reach 93.9%.
Fichier non déposé

Dates et versions

hal-04457949 , version 1 (14-02-2024)

Identifiants

Citer

Haibin Wang, Tian Wang, Mengyi Zhang, Baochang Zhang, Peng Shi, et al.. Point Gated Attention. 2022 China Automation Congress (CAC), Nov 2022, Xiamen, China. pp.2770-2774, ⟨10.1109/CAC57257.2022.10056083⟩. ⟨hal-04457949⟩
10 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More