Gram Regularization For Multi-view 3D Shape Retrieval

Abstract

How to obtain the desirable representation of a 3D shape is a key challenge in 3D shape retrieval task. Most existing 3D shape retrieval methods focus on capturing shape representation with different neural network architectures, while the learning ability of each layer in the network is neglected. A common and tough issue that limits the capacity of the network is overfitting. To tackle this, L2 regularization is applied widely in existing deep learning frameworks. However,the effect on the generalization ability with L2 regularization is limited as it only controls large value in parameters. To make up the gap, in this paper, we propose a novel regularization term called Gram regularization which reinforces the learning ability of the network by encouraging the weight kernels to extract different information on the corresponding feature map. By forcing the variance between weight kernels to be large, the regularizer can help to extract discriminative features. The proposed Gram regul

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2020gram

Related papers

• View N-gram Network For 3D Object Retrieval (2019)13.05
• Joint Learning Of 3D Shape Retrieval And Deformation (2021)11.08
• Angular Triplet-center Loss For Multi-view 3D Shape Retrieval (2018)12.33
• Generalizing Single-view 3D Shape Retrieval To Occlusions And Unseen Objects (2023)5.24
• Learning Discriminative 3D Shape Representations By View Discerning Networks (2018)8.60
• PREMA: Part-based Recurrent Multi-view Aggregation Network For 3D Shape Retrieval (2021)3.58
• Latformer: Locality-aware Point-view Fusion Transformer For 3D Shape Recognition (2021)6.34
• Multi-feature Distance Metric Learning For Non-rigid 3D Shape Retrieval (2019)5.84