# Attend, Infer, Repeat: Fast Scene Understanding with Generative Models

arXiv: https://arxiv.org/abs/1603.08575 · HTML: https://mlsanity.com/paper/1603.08575/

## Key facts

- Cited by 209 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Mar 2016.

## Built on by (most cited first, 30 of 209)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Conditional Object-Centric Learning from Video](https://mlsanity.com/paper/2111.12594/) (2021)
- [Bridging the Gap to Real-World Object-Centric Learning](https://mlsanity.com/paper/2209.14860/) (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)
- [Generative Adversarial Transformers](https://mlsanity.com/paper/2103.01209/) (2021)
- [GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement](https://mlsanity.com/paper/2104.09958/) (2021)
- [Unsupervised Discovery of Object Radiance Fields](https://mlsanity.com/paper/2107.07905/) (2021)
- [Deep Image Deblurring: A Survey](https://mlsanity.com/paper/2201.10700/) (2022)
- [ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation](https://mlsanity.com/paper/2111.10265/) (2021)
- [Object-Centric Slot Diffusion](https://mlsanity.com/paper/2303.10834/) (2023)
- [Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation](https://mlsanity.com/paper/2104.01148/) (2021)
- [SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models](https://mlsanity.com/paper/2305.11281/) (2023)
- [Generalization and Robustness Implications in Object-Centric Learning](https://mlsanity.com/paper/2107.00637/) (2021)
- [SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data](https://mlsanity.com/paper/2103.15619/) (2021)
- [Is Attention Better Than Matrix Decomposition?](https://mlsanity.com/paper/2109.04553/) (2021)
- [Neural Production Systems: Learning Rule-Governed Visual Dynamics](https://mlsanity.com/paper/2103.01937/) (2021)
- [Unsupervised Learning of Compositional Energy Concepts](https://mlsanity.com/paper/2111.03042/) (2021)
- [SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition](https://mlsanity.com/paper/2106.03849/) (2021)
- [Differentiable Patch Selection for Image Recognition](https://mlsanity.com/paper/2104.03059/) (2021)
- [Improving Object-centric Learning with Query Optimization](https://mlsanity.com/paper/2210.08990/) (2022)
- [SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing](https://mlsanity.com/paper/2112.02236/) (2021)
- [Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation](https://mlsanity.com/paper/2307.02598/) (2023)
- [Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames](https://mlsanity.com/paper/2302.04973/) (2023)
- [Unsupervised Layered Image Decomposition into Object Prototypes](https://mlsanity.com/paper/2104.14575/) (2021)
- [An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning](https://mlsanity.com/paper/2302.04419/) (2023)
- [Self-supervised Object-Centric Learning for Videos](https://mlsanity.com/paper/2310.06907/) (2023)
- [SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers](https://mlsanity.com/paper/2312.00648/) (2023)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [Discovering Objects that Can Move](https://mlsanity.com/paper/2203.10159/) (2022)

## Abstract (arXiv)

We present a framework for efficient inference in structured image models that explicitly reason about objects. We achieve this by performing probabilistic inference using a recurrent neural network that attends to scene elements and processes them one at a time. Crucially, the model itself learns to choose the appropriate number of inference steps. We use this scheme to learn to perform inference in partially specified 2D models (variable-sized variational auto-encoders) and fully specified 3D models (probabilistic renderers). We show that such models learn to identify multiple objects - counting, locating and classifying the elements of a scene - without any supervision, e.g., decomposing 3D images with various numbers of objects in a single forward pass of a neural network. We further show that the networks produce accurate inferences when compared to supervised counterparts, and that their structure leads to improved generalization.