mlsanityData to 14 Oct 2026

Random Walks in Self-supervised Learning for Triangular Meshes

arXiv 2503.00816 ↗First posted 2 Mar 2025cs.GR cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 45 of its 72 references that are in the map. First posted on arXiv 2 Mar 2025.

Builds on

45 of 72 references.

References · 45

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  7. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  8. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  9. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  10. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  11. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  12. 2019Contrastive Multiview Codingcited by 1,301
33 more
  1. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  2. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  3. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,066
  4. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
  5. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  6. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 673
  7. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  8. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 504
  9. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  10. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  11. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  12. 2018Tracking Emerges by Colorizing Videoscited by 166
  13. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  14. 2017Pointwise Convolutional Neural Networkscited by 127
  15. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  16. 2015Learning to See by Movingcited by 102
  17. 2018MeshNet: Mesh Neural Network for 3D Shape Representationcited by 95
  18. 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
  19. 2019ClusterFit: Improving Generalization of Visual Representationscited by 82
  20. 2019Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 80
  21. 2019Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Predictioncited by 66
  22. 2016VConv-DAE: Deep Volumetric Shape Learning Without Object Labelscited by 50
  23. 2018Self-Supervised Feature Learning by Learning to Spot Artifactscited by 43
  24. 2018A Simple Approach to Intrinsic Correspondence Learning on Unstructured 3D Meshescited by 39
  25. 2019SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentationcited by 29
  26. 2020Label-Efficient Learning on Point Clouds using Approximate Convex Decompositionscited by 27
  27. 2022Graph Masked Autoencoders with Transformerscited by 10
  28. 2023Bootstrapping Autonomous Driving Radars with Self-Supervised Learningcited by 9
  29. 2019Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering With Graph Convolutional Neural Networkcited by 5
  30. 2019Unsupervised Detection of Distinctive Regions on 3D Shapescited by 5
  31. 2021AttWalk: Attentive Cross-Walks for Deep Mesh Analysiscited by 5
  32. 2022An Asymmetric Contrastive Loss for Handling Imbalanced Datasetscited by 3
  33. 2023MeT: A Graph Transformer for Semantic Segmentation of 3D Meshescited by 3

Built on by

Not cited yet.