mlsanityData to 14 Oct 2026

Self-Supervised Image Representation Learning with Geometric Set Consistency

arXiv 2203.15361 ↗First posted 29 Mar 2022cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Our intuition is that 3D geometric consistency priors such as smooth regions and surface discontinuities may imply consistent semantics or object boundaries, and can act as strong cues to guide the learning of 2D image representations without semantic labels. Specifically, we introduce 3D geometric consistency into a contrastive learning framework to enforce the feature consistency within image views. We propose to use geometric consistency sets as constraints and adapt the InfoNCE loss accordingly. We show that our learned image representations are general. By fine-tuning our pre-trained representations for various 2D image-based downstream tasks, including semantic segmentation, object detection, and instance segmentation on real-world indoor scene datasets, we achieve superior performance compared with state-of-the-art methods.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 44 of its 59 references that are in the map. First posted on arXiv 29 Mar 2022.

Builds on

44 of 59 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  7. 2017Mask R-CNNcited by 7,277
  8. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  9. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  10. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  11. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  12. 2016Pyramid Scene Parsing Networkcited by 2,479
32 more
  1. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  2. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,222
  3. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  4. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  5. 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,214
  6. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  7. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
  8. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  9. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  10. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  11. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  12. 2019Label Propagation for Deep Semi-supervised Learningcited by 289
  13. 20183D-SIS: 3D Semantic Instance Segmentation of RGB-D Scanscited by 217
  14. 2017Colorization as a Proxy Task for Visual Understandingcited by 175
  15. 2018GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloudcited by 146
  16. 2020Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reductioncited by 142
  17. 2020ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votescited by 119
  18. 20183DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentationcited by 118
  19. 2020Virtual Multi-view Fusion for 3D Semantic Segmentationcited by 99
  20. 2021Region Similarity Representation Learningcited by 96
  21. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  22. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  23. 20193D Instance Segmentation via Multi-Task Metric Learningcited by 80
  24. 2021Bootstrapping Semantic Segmentation with Regional Contrastcited by 80
  25. 2020JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Cloudscited by 62
  26. 2021Pri3D: Can 3D Priors Help 2D Representation Learning?cited by 61
  27. 2020FPConv: Learning Local Flattening for Point Convolutioncited by 55
  28. 20213D-to-2D Distillation for Indoor Scene Parsingcited by 48
  29. 2021Contrastive Multimodal Fusion with TupleInfoNCEcited by 43
  30. 2020P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understandingcited by 41
  31. 2020Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discriminationcited by 31
  32. 2018Learning Effective RGB-D Representations for Scene Recognitioncited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 3; 2026: 2.

7 papers.

  1. 2022A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directionscited by 73
  2. 2023Joint Representation Learning for Text and 3D Point Cloudcited by 14
  3. 2025Perspective from a Higher Dimension: Can 3D Geometric Priors Help Visual Floorplan Localization?cited by 4
  4. 2025Perspective from a Broader Context: Can Room Style Knowledge Help Visual Floorplan Localization?cited by 2
  5. 20252D-3D Attention and Entropy for Pose Robust 2D Facial Recognitioncited by 1
  6. 2026ProGS: Towards Progressive Coding for 3D Gaussian Splattingcited by 0
  7. 2026Depth-Guided Contrastive Learning for 2D Representations with 3D Spatial Awarenesscited by 0