# Adaptive Slot Attention: Object Discovery with Dynamic Slot Number

arXiv: https://arxiv.org/abs/2406.09196 · HTML: https://mlsanity.com/paper/2406.09196/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 34 references that are in the map.
- First posted on arXiv 13 Jun 2024.

## Builds on (most cited first, 28 of 28)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [Kubric: A scalable dataset generator](https://mlsanity.com/paper/2203.03570/) (2022)
- [Multi-Object Representation Learning with Iterative Variational Inference](https://mlsanity.com/paper/1903.00450/) (2019)
- [Conditional Object-Centric Learning from Video](https://mlsanity.com/paper/2111.12594/) (2021)
- [GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations](https://mlsanity.com/paper/1907.13052/) (2019)
- [Bridging the Gap to Real-World Object-Centric Learning](https://mlsanity.com/paper/2209.14860/) (2022)
- [Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement](https://mlsanity.com/paper/1903.06059/) (2019)
- [Attend, Infer, Repeat: Fast Scene Understanding with Generative Models](https://mlsanity.com/paper/1603.08575/) (2016)
- [Cut and Learn for Unsupervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2301.11320/) (2023)
- [SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos](https://mlsanity.com/paper/2206.07764/) (2022)
- [Illiterate DALL-E Learns to Compose](https://mlsanity.com/paper/2110.11405/) (2021)
- [Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos](https://mlsanity.com/paper/2205.14065/) (2022)
- [Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects](https://mlsanity.com/paper/1806.01794/) (2018)
- [Differentiable Ranks and Sorting using Optimal Transport](https://mlsanity.com/paper/1905.11885/) (2019)
- [TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut](https://mlsanity.com/paper/2209.00383/) (2022)
- [GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement](https://mlsanity.com/paper/2104.09958/) (2021)
- [FreeSOLO: Learning to Segment Objects without Annotations](https://mlsanity.com/paper/2202.12181/) (2022)
- [Generalization and Robustness Implications in Object-Centric Learning](https://mlsanity.com/paper/2107.00637/) (2021)
- [Differentiable Patch Selection for Image Recognition](https://mlsanity.com/paper/2104.03059/) (2021)
- [Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations](https://mlsanity.com/paper/2207.05027/) (2022)
- [Unsupervised Open-Vocabulary Object Localization in Videos](https://mlsanity.com/paper/2309.09858/) (2023)
- [Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation](https://mlsanity.com/paper/2309.13248/) (2023)

## Built on by (most cited first, 30 of 34)

- [One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos](https://mlsanity.com/paper/2409.19603/) (2024)
- [Temporally Consistent Object-Centric Learning by Contrasting Slots](https://mlsanity.com/paper/2412.14295/) (2024)
- [Object-Centric World Model for Language-Guided Manipulation](https://mlsanity.com/paper/2503.06170/) (2025)
- [MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning](https://mlsanity.com/paper/2505.20772/) (2025)
- [Object-Centric Latent Action Learning](https://mlsanity.com/paper/2502.09680/) (2025)
- [Slot-BERT: Self-supervised Object Discovery in Surgical Video](https://mlsanity.com/paper/2501.12477/) (2025)
- [unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning](https://mlsanity.com/paper/2506.01778/) (2025)
- [FORLA: Federated Object-centric Representation Learning with Slot Attention](https://mlsanity.com/paper/2506.02964/) (2025)
- [Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment](https://mlsanity.com/paper/2601.01224/) (2026)
- [Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning](https://mlsanity.com/paper/2603.22758/) (2026)
- [Neurosymbolic Object-Centric Learning with Distant Supervision](https://mlsanity.com/paper/2506.16129/) (2025)
- [Future Slot Prediction for Unsupervised Object Discovery in Surgical Video](https://mlsanity.com/paper/2507.01882/) (2025)
- [TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation](https://mlsanity.com/paper/2606.13714/) (2026)
- [Selective Synergistic Learning for Video Object-Centric Learning](https://mlsanity.com/paper/2606.15527/) (2026)
- [Rethinking Object-Centric Representations for Video Dynamics Modeling](https://mlsanity.com/paper/2606.23436/) (2026)
- [Hierarchical Compact Clustering Attention (COCA) for Unsupervised Object-Centric Learning](https://mlsanity.com/paper/2505.02071/) (2025)
- [GViT: Representing Images as Gaussians for Visual Recognition](https://mlsanity.com/paper/2506.23532/) (2025)
- [SlotMatch: Distilling Object-Centric Representations for Unsupervised Video Segmentation](https://mlsanity.com/paper/2508.03411/) (2025)
- [Slot Attention-based Feature Filtering for Few-Shot Learning](https://mlsanity.com/paper/2508.09699/) (2025)
- [Leveraging Color Channel Independence for Improved Unsupervised Object Detection](https://mlsanity.com/paper/2412.15150/) (2024)
- [Oh-A-DINO: Understanding and Enhancing Attribute-Level Information in Self-Supervised Object-Centric Representations](https://mlsanity.com/paper/2503.09867/) (2025)
- [SPoT: Subpixel Placement of Tokens in Vision Transformers](https://mlsanity.com/paper/2507.01654/) (2025)
- [Component Adaptive Clustering for Generalized Category Discovery](https://mlsanity.com/paper/2507.01711/) (2025)
- [ContextFusion and Bootstrap: An Effective Approach to Improve Slot Attention-Based Object-Centric Learning](https://mlsanity.com/paper/2509.02032/) (2025)
- [Towards 3D Object-Centric Feature Learning for Semantic Scene Completion](https://mlsanity.com/paper/2511.13031/) (2025)
- [Unsupervised Structural Scene Decomposition via Foreground-Aware Slot Attention with Pseudo-Mask Guidance](https://mlsanity.com/paper/2512.02685/) (2025)
- [QASA: Quality-Guided K-Adaptive Slot Attention for Unsupervised Object-Centric Learning](https://mlsanity.com/paper/2601.12936/) (2026)
- [When Slots Compete: Slot Merging in Object-Centric Learning](https://mlsanity.com/paper/2603.11246/) (2026)
- [HCLSM: Hierarchical Causal Latent State Machines for Object-Centric World Modeling](https://mlsanity.com/paper/2603.29090/) (2026)
- [Collapse-Free Prototype Readout Layer for Transformer Encoders](https://mlsanity.com/paper/2604.03850/) (2026)

## Abstract (arXiv)

Object-centric learning (OCL) extracts the representation of objects with slots, offering an exceptional blend of flexibility and interpretability for abstracting low-level perceptual features. A widely adopted method within OCL is slot attention, which utilizes attention mechanisms to iteratively refine slot representations. However, a major drawback of most object-centric models, including slot attention, is their reliance on predefining the number of slots. This not only necessitates prior knowledge of the dataset but also overlooks the inherent variability in the number of objects present in each instance. To overcome this fundamental limitation, we present a novel complexity-aware object auto-encoder framework. Within this framework, we introduce an adaptive slot attention (AdaSlot) mechanism that dynamically determines the optimal number of slots based on the content of the data. This is achieved by proposing a discrete slot sampling module that is responsible for selecting an appropriate number of slots from a candidate list. Furthermore, we introduce a masked slot decoder that suppresses unselected slots during the decoding process. Our framework, tested extensively on object discovery tasks with various datasets, shows performance matching or exceeding top fixed-slot models. Moreover, our analysis substantiates that our method exhibits the capability to dynamically adapt the slot number according to each instance's complexity, offering the potential for further exploration in slot attention research. Project will be available at https://kfan21.github.io/AdaSlot/