Angular Triplet-center Loss For Multi-view 3D Shape Retrieval

Abstract

How to obtain the desirable representation of a 3D shape, which is discriminative across categories and polymerized within classes, is a significant challenge in 3D shape retrieval. Most existing 3D shape retrieval methods focus on capturing strong discriminative shape representation with softmax loss for the classification task, while the shape feature learning with metric loss is neglected for 3D shape retrieval. In this paper, we address this problem based on the intuition that the cosine distance of shape embeddings should be close enough within the same class and far away across categories. Since most of 3D shape retrieval tasks use cosine distance of shape features for measuring shape similarity, we propose a novel metric loss named angular triplet-center loss, which directly optimizes the cosine distances between the features. It inherits the triplet-center loss property to achieve larger inter-class distance and smaller intra-class distance simultaneously. Unlike previous metri

Stats

• citations43
• S2 citations—
• github stars0
• HF likes0
• heat score12.33
• arxiv keyli2018angular

Related papers

• Triplet-center Loss For Multi-view 3D Object Retrieval (2018)18.70
• Rethinking Loss Design For Large-scale 3D Shape Retrieval (2019)4.52
• Multi-feature Distance Metric Learning For Non-rigid 3D Shape Retrieval (2019)5.84
• Gram Regularization For Multi-view 3D Shape Retrieval (2020)0.00
• Learning With Batch-wise Optimal Transport Loss For 3D Shape Recognition (2019)10.48
• Structure-aware 3D VR Sketch To 3D Shape Retrieval (2022)8.94
• Tricolo: Trimodal Contrastive Loss For Text To Shape Retrieval (2022)8.09
• Joint Learning Of 3D Shape Retrieval And Deformation (2021)11.08