# Disentangling Visual Priors: Unsupervised Learning of Scene Interpretations with Compositional Autoencoder

arXiv: https://arxiv.org/abs/2409.09716 · HTML: https://mlsanity.com/paper/2409.09716/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 15 Sep 2024.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [SCOPS: Self-Supervised Co-Part Segmentation](https://mlsanity.com/paper/1905.01298/) (2019)
- [Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research](https://mlsanity.com/paper/1911.05063/) (2019)
- [Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks](https://mlsanity.com/paper/2310.19909/) (2023)
- [Unsupervised Part Discovery from Contrastive Reconstruction](https://mlsanity.com/paper/2111.06349/) (2021)
- [Compositional Scene Representation Learning via Reconstruction: A Survey](https://mlsanity.com/paper/2202.07135/) (2022)
- [Weakly Supervised Learning of Multi-Object 3D Scene Decompositions Using Deep Shape Priors](https://mlsanity.com/paper/2010.04030/) (2020)

## Built on by (most cited first, 2 of 2)

- [Autoassociative Learning of Structural Representations for Modeling and Classification in Medical Imaging](https://mlsanity.com/paper/2411.12070/) (2024)
- [Generative Learning of Differentiable Object Models for Compositional Interpretation of Complex Scenes](https://mlsanity.com/paper/2506.08191/) (2025)

## Abstract (arXiv)

Contemporary deep learning architectures lack principled means for capturing and handling fundamental visual concepts, like objects, shapes, geometric transforms, and other higher-level structures. We propose a neurosymbolic architecture that uses a domain-specific language to capture selected priors of image formation, including object shape, appearance, categorization, and geometric transforms. We express template programs in that language and learn their parameterization with features extracted from the scene by a convolutional neural network. When executed, the parameterized program produces geometric primitives which are rendered and assessed for correspondence with the scene content and trained via auto-association with gradient. We confront our approach with a baseline method on a synthetic benchmark and demonstrate its capacity to disentangle selected aspects of the image formation process, learn from small data, correct inference in the presence of noise, and out-of-sample generalization.