Rethinking Loss Design For Large-scale 3D Shape Retrieval

Abstract

Learning discriminative shape representations is a crucial issue for large-scale 3D shape retrieval. In this paper, we propose the Collaborative Inner Product Loss (CIP Loss) to obtain ideal shape embedding that discriminative among different categories and clustered within the same class. Utilizing simple inner product operation, CIP loss explicitly enforces the features of the same class to be clustered in a linear subspace, while inter-class subspaces are constrained to be at least orthogonal. Compared to previous metric loss functions, CIP loss could provide more clear geometric interpretation for the embedding than Euclidean margin, and is easy to implement without normalization operation referring to cosine margin. Moreover, our proposed loss term can combine with other commonly used loss functions and can be easily plugged into existing off-the-shelf architectures. Extensive experiments conducted on the two public 3D object retrieval datasets, ModelNet and ShapeNetCore 55, demon

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyli2019rethinking

Related papers

• Angular Triplet-center Loss For Multi-view 3D Shape Retrieval (2018)12.33
• Triplet-center Loss For Multi-view 3D Object Retrieval (2018)18.70
• Joint Learning Of 3D Shape Retrieval And Deformation (2021)11.08
• Risa-net: Rotation-invariant Structure-aware Network For Fine-grained 3D Shape Retrieval (2020)5.48
• Zero In On Shape: A Generic 2D-3D Instance Similarity Metric Learned From Synthetic Data (2021)5.84
• Multi-feature Distance Metric Learning For Non-rigid 3D Shape Retrieval (2019)5.84
• Optimizing Multi-modal Models For Image-based Shape Retrieval: The Role Of Pre-alignment And Hard Contrastive Learning (2026)0.00
• Structure-aware 3D VR Sketch To 3D Shape Retrieval (2022)8.94