Triplet-Center Loss for Multi-View 3D Object Retrieval

TL;DR

This paper introduces a novel triplet-center loss for 3D object retrieval that improves discriminative feature learning by combining class centers with triplet constraints, outperforming existing methods.

Contribution

The paper proposes a new triplet-center loss that enhances feature discrimination in 3D object retrieval, demonstrating superior performance over state-of-the-art approaches.

Findings

Significant improvement on 3D object retrieval benchmarks

Effective in sketch-based 3D shape retrieval

Outperforms existing deep metric learning losses

Abstract

Most existing 3D object recognition algorithms focus on leveraging the strong discriminative power of deep learning models with softmax loss for the classification of 3D data, while learning discriminative features with deep metric learning for 3D object retrieval is more or less neglected. In the paper, we study variants of deep metric learning losses for 3D object retrieval, which did not receive enough attention from this area. First , two kinds of representative losses, triplet loss and center loss, are introduced which could learn more discriminative features than traditional classification loss. Then, we propose a novel loss named triplet-center loss, which can further enhance the discriminative power of the features. The proposed triplet-center loss learns a center for each class and requires that the distances between samples and centers from the same class are closer than those from different classes. Extensive experimental results on two popular 3D object retrieval benchmarks and two widely-adopted sketch-based 3D shape retrieval benchmarks consistently demonstrate the effectiveness of our proposed loss, and significant improvements have been achieved compared with the state-of-the-arts.