# Binding via Reconstruction Clustering

arXiv: https://arxiv.org/abs/1511.06418 · HTML: https://mlsanity.com/paper/1511.06418/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2015.

## Built on by (most cited first, 16 of 16)

- [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)
- [Provably Learning Object-Centric Representations](https://mlsanity.com/paper/2305.14229/) (2023)
- [Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations](https://mlsanity.com/paper/2106.03630/) (2021)
- [Compositional Scene Representation Learning via Reconstruction: A Survey](https://mlsanity.com/paper/2202.07135/) (2022)
- [Interaction Asymmetry: A General Principle for Learning Composable Abstractions](https://mlsanity.com/paper/2411.07784/) (2024)
- [Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns](https://mlsanity.com/paper/2210.12148/) (2022)
- [Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter](https://mlsanity.com/paper/2208.03374/) (2022)
- [Sensitivity of Slot-Based Object-Centric Models to their Number of Slots](https://mlsanity.com/paper/2305.18890/) (2023)
- [Robust and Controllable Object-Centric Learning through Energy-based Models](https://mlsanity.com/paper/2210.05519/) (2022)
- [Knowledge-Guided Object Discovery with Acquired Deep Impressions](https://mlsanity.com/paper/2103.10611/) (2021)
- [Dance of SNN and ANN: Solving binding problem by combining spike timing and reconstructive attention](https://mlsanity.com/paper/2211.06027/) (2022)
- [Compositional Scene Modeling with Global Object-Centric Representations](https://mlsanity.com/paper/2211.11500/) (2022)
- [Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?](https://mlsanity.com/paper/2212.10292/) (2022)
- [Dialectics for Artificial Intelligence](https://mlsanity.com/paper/2512.17373/) (2025)
- [Deep Sprite-based Image Models: An Analysis](https://mlsanity.com/paper/2604.19480/) (2026)

## Abstract (arXiv)

Disentangled distributed representations of data are desirable for machine learning, since they are more expressive and can generalize from fewer examples. However, for complex data, the distributed representations of multiple objects present in the same input can interfere and lead to ambiguities, which is commonly referred to as the binding problem. We argue for the importance of the binding problem to the field of representation learning, and develop a probabilistic framework that explicitly models inputs as a composition of multiple objects. We propose an unsupervised algorithm that uses denoising autoencoders to dynamically bind features together in multi-object inputs through an Expectation-Maximization-like clustering process. The effectiveness of this method is demonstrated on artificially generated datasets of binary images, showing that it can even generalize to bind together new objects never seen by the autoencoder during training.