Adaptive Channel Encoding Transformer for Point Cloud Analysis

• DOI: 10.48550/arxiv.2112.02507
• Publication Date: 2021-01-01
• Authors: Guoquan Xu; Hezhi Cao; Jianwei Wan; Ke Xu; Yanxin Ma; Cong Zhang
• Keywords: ENCODE

Transformer plays an increasingly important role in various computer vision areas and remarkable achievements have also been made point cloud analysis. Since they mainly focus on point-wise transformer, adaptive channel encoding transformer is proposed this paper. Specifically, a convolution called Transformer-Conv designed to encode the channel. It can feature channels by capturing potential relationship between coordinates features. Compared with simply assigning attention weight each channel, our method aims adaptively. In addition, network adopts neighborhood search of low-level high-level dual semantic receptive fields improve performance. Extensive experiments show that superior state-of-the-art classification segmentation methods three benchmark datasets.