Gram Regularization for Multi-view 3D Shape Retrieval

11/16/2020
by   Zhaoqun Li, et al.
0

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 regularization is data independent and can converge stably and quickly without bells and whistles. Moreover, it can be easily plugged into existing off-the-shelf architectures. Extensive experimental results on the popular 3D object retrieval benchmark ModelNet demonstrate the effectiveness of our method.

READ FULL TEXT
research
08/06/2019

View N-gram Network for 3D Object Retrieval

How to aggregate multi-view representations of a 3D shape object into an...
research
11/21/2018

Angular Triplet-Center Loss for Multi-view 3D Shape Retrieval

How to obtain the desirable representation of a 3D shape, which is discr...
research
12/10/2020

Auto-MVCNN: Neural Architecture Search for Multi-view 3D Shape Recognition

In 3D shape recognition, multi-view based methods leverage human's persp...
research
06/06/2020

MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Angles

The strong correlation between neurons or filters can significantly weak...
research
09/26/2019

Convolutional Neural Networks with Dynamic Regularization

Regularization is commonly used in machine learning for alleviating over...
research
06/03/2019

Rethinking Loss Design for Large-scale 3D Shape Retrieval

Learning discriminative shape representations is a crucial issue for lar...
research
08/11/2018

Learning Discriminative 3D Shape Representations by View Discerning Networks

In view-based 3D shape recognition, extracting discriminative visual rep...

Please sign up or login with your details

Forgot password? Click here to reset