mlsanityData to 7 Oct 2026

SEMPART: Self-supervised Multi-resolution Partitioning of Image Semantics

arXiv 2309.10972 ↗First posted 20 Sep 2023cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Accurately determining salient regions of an image is challenging when labeled data is scarce. DINO-based self-supervised approaches have recently leveraged meaningful image semantics captured by patch-wise features for locating foreground objects. Recent methods have also incorporated intuitive priors and demonstrated value in unsupervised methods for object partitioning. In this paper, we propose SEMPART, which jointly infers coarse and fine bi-partitions over an image's DINO-based semantic graph. Furthermore, SEMPART preserves fine boundary details using graph-driven regularization and successfully distills the coarse mask semantics into the fine mask. Our salient object detection and single object localization findings suggest that SEMPART produces high-quality masks rapidly without additional post-processing and benefits from co-optimizing the coarse and fine branches.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 43 of its 62 references that are in the map. First posted on arXiv 20 Sep 2023.

Builds on

43 of 62 references.

References · 43

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  7. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  8. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  9. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  10. 2020U2-Net: Going Deeper with Nested U-Structure for Salient Object Detectioncited by 410
  11. 2017Graph Signal Processing: Overview, Challenges and Applicationscited by 409
  12. 2019SOLO: Segmenting Objects by Locationscited by 289
31 more
  1. 2020Unsupervised Discovery of Interpretable Directions in the GAN Latent Spacecited by 288
  2. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  3. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 227
  4. 2019Salient Object Detection in the Deep Learning Era: An In-Depth Surveycited by 163
  5. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
  6. 2018Normalized Cut Loss for Weakly-supervised CNN Segmentationcited by 112
  7. 2022TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cutcited by 111
  8. 2022FreeSOLO: Learning to Segment Objects without Annotationscited by 102
  9. 2014Salient Object Detection: A Surveycited by 98
  10. 2015The Fast Bilateral Solvercited by 86
  11. 2019Unsupervised Object Segmentation by Redrawingcited by 74
  12. 2022Unsupervised Object Localization: Observing the Background to Discover Objectscited by 66
  13. 2018Image Restoration using Total Variation Regularized Deep Image Priorcited by 65
  14. 2020Toward unsupervised, multi-object discovery in large-scale image collectionscited by 65
  15. 2022Unsupervised Salient Object Detection with Spectral Cluster Votingcited by 56
  16. 2021Large-Scale Unsupervised Object Discoverycited by 54
  17. 2020Object Segmentation Without Labels with Large-Scale Generative Modelscited by 52
  18. 2021Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Modelscited by 44
  19. 2022Learning Graph Regularisation for Guided Super-Resolutioncited by 27
  20. 2022DeepCut: Unsupervised Segmentation using Graph Neural Networks Clusteringcited by 25
  21. 2020Information-Theoretic Segmentation by Inpainting Error Maximizationcited by 22
  22. 2022SelfReformer: Self-Refined Network with Transformer for Salient Object Detectioncited by 20
  23. 2022NamedMask: Distilling Segmenters from Complementary Foundation Modelscited by 20
  24. 2022MOVE: Unsupervised Movable Object Segmentation and Detectioncited by 20
  25. 2022FEAT: Face Editing with Attentioncited by 16
  26. 2017Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transformingcited by 15
  27. 2020Unrolling of Deep Graph Total Variation for Image Denoisingcited by 12
  28. 2021Graph Partitioning and Sparse Matrix Ordering using Reinforcement Learning and Graph Neural Networkscited by 8
  29. 2016Total Variation Applications in Computer Visioncited by 6
  30. 2021Deep Learning and Spectral Embedding for Graph Partitioningcited by 5
  31. 2023CoralStyleCLIP: Co-optimized Region and Layer Selection for Image Editingcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 2.

4 papers.

  1. 2023Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Surveycited by 16
  2. 2024Unsupervised Part Discovery via Dual Representation Alignmentcited by 2
  3. 2025FlowCut: Unsupervised Video Instance Segmentation via Temporal Mask Matchingcited by 2
  4. 2025Towards Open World Detection: A Surveycited by 0