Random Walks in Self-supervised Learning for Triangular Meshes
This work addresses the problem of 3D mesh analysis for researchers and practitioners in computer vision, but it is incremental as it builds on existing self-supervised and contrastive learning methods.
The study tackled self-supervised learning for 3D mesh analysis by using random walks for data augmentation and combining contrastive and clustering losses, resulting in improved performance as evaluated by mean Average Precision scores and a supervised SVM classifier.
This study addresses the challenge of self-supervised learning for 3D mesh analysis. It presents an new approach that uses random walks as a form of data augmentation to generate diverse representations of mesh surfaces. Furthermore, it employs a combination of contrastive and clustering losses. The contrastive learning framework maximizes similarity between augmented instances of the same mesh while minimizing similarity between different meshes. We integrate this with a clustering loss, enhancing class distinction across training epochs and mitigating training variance. Our model's effectiveness is evaluated using mean Average Precision (mAP) scores and a supervised SVM linear classifier on extracted features, demonstrating its potential for various downstream tasks such as object classification and shape retrieval.