mlsanityData to 14 Oct 2026

SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers

arXiv 2312.00648 ↗First posted 1 Dec 2023cs.CVcited by 49

Not on the map. Why?

Abstract (arXiv)

Unsupervised object-centric learning aims to decompose scenes into interpretable object entities, termed slots. Slot-based auto-encoders stand out as a prominent method for this task. Within them, crucial aspects include guiding the encoder to generate object-specific slots and ensuring the decoder utilizes them during reconstruction. This work introduces two novel techniques, (i) an attention-based self-training approach, which distills superior slot-based attention masks from the decoder to the encoder, enhancing object segmentation, and (ii) an innovative patch-order permutation strategy for autoregressive transformers that strengthens the role of slot vectors in reconstruction. The effectiveness of these strategies is showcased experimentally. The combined approach significantly surpasses prior slot-based autoencoder methods in unsupervised object segmentation, especially with complex real-world images. We provide the implementation code at https://github.com/gkakogeorgiou/spot .

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Builds on 67 of its 82 references that are in the map. First posted on arXiv 1 Dec 2023.

Builds on

67 of 82 references.

References · 67

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  7. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  8. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  9. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  10. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  11. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
  12. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
38 more
  1. 2020Object-Centric Learning with Slot Attentioncited by 876
  2. 2016Conditional Image Generation with PixelCNN Decoderscited by 862
  3. 2016Pixel Recurrent Neural Networkscited by 816
  4. 2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 531
  5. 2022Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priorscited by 487
  6. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
  7. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 392
  8. 2022Kubric: A scalable dataset generatorcited by 381
  9. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 360
  10. 2021Conditional Object-Centric Learning from Videocited by 248
  11. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  12. 2019Billion-scale semi-supervised learning for image classificationcited by 232
  13. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 230
  14. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  15. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 220
  16. 2016Attend, Infer, Repeat: Fast Scene Understanding with Generative Modelscited by 209
  17. 2020SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decompositioncited by 190
  18. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  19. 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 187
  20. 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
  21. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 175
  22. 2023Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuningcited by 170
  23. 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 166
  24. 2021Efficient Visual Pretraining with Contrastive Detectioncited by 150
  25. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
  26. 2021Illiterate DALL-E Learns to Composecited by 147
  27. 2022SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Modelscited by 147
  28. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  29. 2021Cycle Self-Training for Domain Adaptationcited by 120
  30. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
  31. 2023Object-Centric Slot Diffusioncited by 90
  32. 2023Image Captioners Are Scalable Vision Learners Toocited by 89
  33. 2023SlotDiffusion: Object-Centric Generative Modeling with Diffusion Modelscited by 85
  34. 2022Object discovery and representation networkscited by 80
  35. 2023Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similaritiescited by 78
  36. 2022Self-Supervised Visual Representation Learning with Semantic Groupingcited by 70
  37. 2022Unsupervised Object Localization: Observing the Background to Discover Objectscited by 66
  38. 2022Improving Object-centric Learning with Query Optimizationcited by 60

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 11; 2025: 13; 2026: 25.

49 papers.

Sort:

By area:

  1. 2024DINO-Foresight: Looking into the Future with DINOcited by 45
  2. 2024Artificial Kuramoto Oscillatory Neuronscited by 38
  3. 2024Temporally Consistent Object-Centric Learning by Contrasting Slotscited by 31
  4. 2024σ-GPTs: A New Approach to Autoregressive Modelscited by 20
  5. 2024Zero-Shot Object-Centric Representation Learningcited by 19
  6. 2025Multi-Token Prediction Needs Registerscited by 16
  7. 2026Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modelingcited by 15
  8. 2024GLASS: Guided Latent Slot Diffusion for Object-Centric Learningcited by 14
  9. 2025Slot Attention with Re-Initialization and Self-Distillationcited by 14
  10. 2025Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generationcited by 13
  11. 2025Predicting Video Slot Attention Queries from Random Slot-Feature Pairscited by 12
  12. 2025Vector-Quantized Vision Foundation Models for Object-Centric Learningcited by 11
37 more
  1. 2025MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learningcited by 11
  2. 2024Identifiable Object-Centric Representation Learning via Probabilistic Slot Attentioncited by 9
  3. 2024Bootstrapping Top-down Information for Self-modulating Slot Attentioncited by 6
  4. 2025Object-Centric Pretraining via Target Encoder Bootstrappingcited by 6
  5. 2025Smoothing Slot Attention Iterations and Recurrencescited by 6
  6. 2024Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biasescited by 5
  7. 2024Grouped Discrete Representation for Object-Centric Learningcited by 5
  8. 2026From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric Learningcited by 5
  9. 2025Motion-Refined DINOSAUR for Unsupervised Multi-Object Discoverycited by 4
  10. 2024Top-Down Guidance for Learning Object-Centric Representationscited by 3
  11. 2025FORLA: Federated Object-centric Representation Learning with Slot Attentioncited by 3
  12. 2026Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignmentcited by 3
  13. 2026Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learningcited by 3
  14. 2026Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learningcited by 2
  15. 2026TSA: Temporal Slot Activation for Persistent Object-Centric Video Representationcited by 2
  16. 2026Rethinking Object-Centric Representations for Video Dynamics Modelingcited by 2
  17. 2025Object-Centric Vision Token Pruning for Vision Language Modelscited by 1
  18. 2026MUFASA: A Multi-Layer Framework for Slot Attentioncited by 1
  19. 2026A Hyperbolic Perspective on Hierarchical Structure in Object-Centric Scene Representationscited by 1
  20. 2026SSR: Similarity-Shift Refinement for Training-Free Object-Centric Maskscited by 1
  21. 2025Clink! Chop! Thud! -- Learning Object Sounds from Real-World Interactionscited by 0
  22. 2025Unsupervised Structural Scene Decomposition via Foreground-Aware Slot Attention with Pseudo-Mask Guidancecited by 0
  23. 2026QASA: Quality-Guided K-Adaptive Slot Attention for Unsupervised Object-Centric Learningcited by 0
  24. 2026Evaluating Object-Centric Models beyond Object Discoverycited by 0
  25. 2026ORGAN: Object-Centric Representation Learning using Cycle Consistent Generative Adversarial Networkscited by 0
  26. 2026VINO: Video-driven Invariance for Non-contextual Objects via Structural Prior Guided De-contextualizationcited by 0
  27. 2026When Slots Compete: Slot Merging in Object-Centric Learningcited by 0
  28. 2026Deep Sprite-based Image Models: An Analysiscited by 0
  29. 2026DenseTRF: Texture-Aware Unsupervised Representation Adaptation for Surgical Scene Dense Predictioncited by 0
  30. 2026What-Where Transformer: A Slot-Centric Visual Backbone for Concurrent Representation and Localizationcited by 0
  31. 2026Cycle Consistency in Video Object-Centric Learningcited by 0
  32. 2026HSA: Hierarchical Slot Attention for Multi-granularity Scene-Decompositioncited by 0
  33. 2026More Structure, Not More Capacity: Object-Centric Representations for Visuomotor Imitation Learningcited by 0
  34. 2026Slot-RAE: Streamlining Object-Centric Learning via Direct Representation Auto-Encoderscited by 0
  35. 2026Semantic Slots for Video Object-Centric Learningcited by 0
  36. 2026Does Attention-Guided Masking Really Help Object Discovery in Object-Centric Learning?cited by 0
  37. 2026SlotDiT: Object-Centric Representations for Diffusion Transformerscited by 0