mlsanityData to 7 Oct 2026

Seg-HGNN: Unsupervised and Light-Weight Image Segmentation with Hyperbolic Graph Neural Networks

arXiv 2409.06589 ↗First posted 10 Sep 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Image analysis in the euclidean space through linear hyperspaces is well studied. However, in the quest for more effective image representations, we turn to hyperbolic manifolds. They provide a compelling alternative to capture complex hierarchical relationships in images with remarkably small dimensionality. To demonstrate hyperbolic embeddings' competence, we introduce a light-weight hyperbolic graph neural network for image segmentation, encompassing patch-level features in a very small embedding size. Our solution, Seg-HGNN, surpasses the current best unsupervised method by 2.5%, 4% on VOC-07, VOC-12 for localization, and by 0.8%, 1.3% on CUB-200, ECSSD for segmentation, respectively. With less than 7.5k trainable parameters, Seg-HGNN delivers effective and fast (≈ 2 images/second) results on very standard GPUs like the GTX1650. This empirical evaluation presents compelling evidence of the efficacy and potential of hyperbolic representations for vision tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 52 references that are in the map. First posted on arXiv 10 Sep 2024.

Builds on

36 of 52 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  8. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  9. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
  10. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  11. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 954
  12. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
24 more
  1. 2019Hyperbolic Graph Convolutional Neural Networkscited by 400
  2. 2018Hyperbolic Neural Networkscited by 393
  3. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  4. 2021Deep ViT Features as Dense Visual Descriptorscited by 327
  5. 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 261
  6. 2019Hyperbolic Graph Neural Networkscited by 244
  7. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 227
  8. 2013OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networkscited by 224
  9. 2019Hyperbolic Image Embeddingscited by 219
  10. 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 166
  11. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
  12. 2022Hyperbolic Image Segmentationcited by 101
  13. 2019SCOPS: Self-Supervised Co-Part Segmentationcited by 100
  14. 2020Interpretable and Accurate Fine-grained Recognition via Region Groupingcited by 75
  15. 2018Deep Feature Factorization For Concept Discoverycited by 64
  16. 2019Dual Graph Convolutional Network for Semantic Segmentationcited by 59
  17. 2021Unsupervised Part Discovery from Contrastive Reconstructioncited by 57
  18. 2021A Hyperbolic-to-Hyperbolic Graph Convolutional Networkcited by 53
  19. 2020Object Segmentation Without Labels with Large-Scale Generative Modelscited by 52
  20. 2020Class-wise Dynamic Graph Convolution for Semantic Segmentationcited by 44
  21. 2019OneGAN: Simultaneous Unsupervised Learning of Conditional Image Generation, Foreground Segmentation, and Fine-Grained Clusteringcited by 28
  22. 2022DeepCut: Unsupervised Segmentation using Graph Neural Networks Clusteringcited by 25
  23. 2021Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoderscited by 15
  24. 2020Riemannian Optimization on the Symplectic Stiefel Manifoldcited by 8

Built on by

Not cited yet.