3D Object Representation Learning: A Set-to-Set Matching Perspective

Tan Yu

doi:10.1109/TIP.2021.3049968

3D Object Representation Learning: A Set-to-Set Matching Perspective

2021-01-01

14

PRE

AI

DOI：10.1109/TIP.2021.3049968

Original

Original request for help

Save

Abstract

En 中文

In this paper, we tackle the 3D object representation learning from the perspective of set-to-set matching. Given two 3D objects, calculating their similarity is formulated as the problem of set-to-set similarity measurement between two set of local patches. As local convolutional features from convolutional feature maps are natural representations of local patches, the set-to-set matching between sets of local patches is further converted into a local features pooling problem. To highlight good matchings and suppress the bad ones, we exploit two pooling methods: 1) bilinear pooling and 2) VLAD pooling. We analyze their effectiveness in enhancing the set-to-set matching and meanwhile establish their connection. Moreover, to balance different components inherent in a bilinear-pooled feature, we propose the harmonized bilinear pooling operation, which follows the spirits of intra-normalization used in VLAD pooling. To achieve an end-to-end trainable framework, we implement the proposed harmonized bilinear pooling and intra-normalized VLAD as two layers to construct two types of neural network, multi-view harmonized bilinear network (MHBN) and multi-view VLAD network (MVLADN). Systematic experiments conducted on two public benchmark datasets demonstrate the efficacy of the proposed MHBN and MVLADN in 3D object recognition.

Keywords:

Three-dimensional displays

Kernel

Object recognition

Neural networks

Feature extraction

Two dimensional displays

Convolutional neural networks

3D object recognition

convolutional neural network

bilinear pooling

3D Object Representation Learning: A Set-to-Set Matching Perspective

Abstract

AI Summary

Journal

Organization