Robust Attentional Pooling via Feature Selection

Jianbo Zheng, Teng Yok Lee, Chen Feng, Xiaohua Lit, Ziming Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper we propose a novel network module, namely Robust Attentional Pooling (RAP), that potentially can be applied in an arbitrary network for generating single vector representations for classification. By taking a feature matrix for each data sample as the input, our RAP learns data-dependent weights that are used to generate a vector through linear transformations of the feature matrix. We utilize feature selection to control the sparsity in weights for compressing the data matrices as well as enhancing the robustness of attentional pooling. As exemplary applications, we plug RAP into PointNet and ResNet for point cloud and image recognition, respectively. We demonstrate that our RAP significantly improves the recognition performance for both networks whenever sparsity is high. For instance, in extreme cases where only one feature per matrix is selected for recognition, RAP achieves more than 60% improvement over PointNet in terms of accuracy on the ModelNet40 dataset.

Original languageEnglish (US)
Title of host publication2018 24th International Conference on Pattern Recognition, ICPR 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2038-2043
Number of pages6
ISBN (Electronic)9781538637883
DOIs
StatePublished - Nov 26 2018
Event24th International Conference on Pattern Recognition, ICPR 2018 - Beijing, China
Duration: Aug 20 2018Aug 24 2018

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume2018-August
ISSN (Print)1051-4651

Other

Other24th International Conference on Pattern Recognition, ICPR 2018
CountryChina
CityBeijing
Period8/20/188/24/18

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Robust Attentional Pooling via Feature Selection'. Together they form a unique fingerprint.

Cite this