3D Cross-Modal Retrieval Using Noisy Center Loss and SimSiam for Small Batch Training

• Yeon-Seung Choo,
• Boeun Kim,
• Hyun-Sik Kim,
• Yong-Suk Park,

Vol. 18, No. 3, March 31, 2024
10.3837/tiis.2024.03.008, Download Paper (Free):

• center loss
• Cross-Modal
• object retrieval
• representation learning
• Self-Supervised Learning
• Supervised Learning

Abstract

3D Cross-Modal Retrieval (3DCMR) is a task that retrieves 3D objects regardless of modalities, such as images, meshes, and point clouds. One of the most prominent methods used for 3DCMR is the Cross-Modal Center Loss Function (CLF) which applies the conventional center loss strategy for 3D cross-modal search and retrieval. Since CLF is based on center loss, the center features in CLF are also susceptible to subtle changes in hyperparameters and external inferences. For instance, performance degradation is observed when the batch size is too small. Furthermore, the Mean Squared Error (MSE) used in CLF is unable to adapt to changes in batch size and is vulnerable to data variations that occur during actual inference due to the use of simple Euclidean distance between multi-modal features. To address the problems that arise from small batch training, we propose a Noisy Center Loss (NCL) method to estimate the optimal center features. In addition, we apply the simple Siamese representation learning method (SimSiam) during optimal center feature estimation to compare projected features, making the proposed method robust to changes in batch size and variations in data. As a result, the proposed approach demonstrates improved performance in ModelNet40 dataset compared to the conventional methods.

Statistics

Cite this article