mlsanityData to 7 Oct 2026

Unsupervised Multi-object Segmentation Using Attention and Soft-argmax

arXiv 2205.13271 ↗First posted 26 May 2022cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

We introduce a new architecture for unsupervised object-centric representation learning and multi-object detection and segmentation, which uses a translation-equivariant attention mechanism to predict the coordinates of the objects present in the scene and to associate a feature vector to each object. A transformer encoder handles occlusions and redundant detections, and a convolutional autoencoder is in charge of background reconstruction. We show that this architecture significantly outperforms the state of the art on complex synthetic benchmarks.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 49 of its 59 references that are in the map. First posted on arXiv 26 May 2022.

Builds on

49 of 59 references.

References · 49

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2017Mask R-CNNcited by 7,259
  5. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  6. 2015Fast R-CNNcited by 2,930
  7. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  8. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  9. 2018Group Normalizationcited by 1,514
  10. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  11. 2015Spatial Transformer Networkscited by 1,423
  12. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
37 more
  1. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  2. 2020Object-Centric Learning with Slot Attentioncited by 865
  3. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  4. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  5. 2019Cascade R-CNN: High Quality Object Detection and Instance Segmentationcited by 428
  6. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  7. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 359
  8. 2017Integral Human Pose Regressioncited by 255
  9. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  10. 2016Attend, Infer, Repeat: Fast Scene Understanding with Generative Modelscited by 209
  11. 2020SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decompositioncited by 190
  12. 2015Deep Spatial Autoencoders for Visuomotor Learningcited by 149
  13. 2018Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objectscited by 128
  14. 2019Entity Abstraction in Visual Model-Based Reinforcement Learningcited by 110
  15. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  16. 2019SCALOR: Generative World Models with Scalable Object Representationscited by 108
  17. 2018Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactionscited by 100
  18. 2019SegSort: Segmentation by Discriminative Sorting of Segmentscited by 96
  19. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
  20. 2019Unsupervised Object Segmentation by Redrawingcited by 74
  21. 2017Continuously Differentiable Exponential Linear Unitscited by 73
  22. 2016Tagger: Deep Unsupervised Perceptual Groupingcited by 69
  23. 2021SOLQ: Segmenting Objects by Learning Queriescited by 68
  24. 2020Attention over learned object embeddings enables complex visual reasoningcited by 59
  25. 2019Emergence of Object Segmentation in Perturbed Generative Modelscited by 57
  26. 2020Generative Neurosymbolic Machinescited by 57
  27. 2018ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stackingcited by 55
  28. 2017Human Pose Regression by Combining Indirect Part Detection and Contextual Informationcited by 52
  29. 2021Unsupervised Layered Image Decomposition into Object Prototypescited by 50
  30. 2019CBNet: A Novel Composite Backbone Network Architecture for Object Detectioncited by 44
  31. 2020Self-supervised Visual Reinforcement Learning with Object-centric Representationscited by 43
  32. 2017Improving Landmark Localization with Semi-Supervised Learningcited by 39
  33. 2021Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representationscited by 36
  34. 2021MarioNette: Self-Supervised Sprite Learningcited by 35
  35. 2015Learning to Linearize Under Uncertaintycited by 25
  36. 2019KNEEL: Knee Anatomical Landmark Localization Using Hourglass Networkscited by 14
  37. 2021Autoencoder-based background reconstruction and foreground segmentation with background noise estimationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 5; 2025: 0; 2026: 1.

11 papers.

  1. 2022Unsupervised Object Localization: Observing the Background to Discover Objectscited by 66
  2. 2023Invariant Slot Attention: Object Discovery with Slot-Centric Reference Framescited by 51
  3. 2024Artificial Kuramoto Oscillatory Neuronscited by 37
  4. 2024Composing Pre-Trained Object-Centric Representations for Robotics From "What" and "Where" Foundation Modelscited by 16
  5. 2023Weakly-supervised Contrastive Learning for Unsupervised Object Discoverycited by 12
  6. 2023Benchmarks for Physical Reasoning AIcited by 8
  7. 2024Recasting Generic Pretrained Vision Transformers As Object-Centric Scene Encoders For Manipulation Policiescited by 6
  8. 2022Learning Explicit Object-Centric Representations with Vision Transformerscited by 1
  9. 2024Historical Printed Ornaments: Dataset and Taskscited by 0
  10. 2024OLAF: A Plug-and-Play Framework for Enhanced Multi-object Multi-part Scene Parsingcited by 0
  11. 2026Deep Sprite-based Image Models: An Analysiscited by 0