# Early Visual Concept Learning with Unsupervised Deep Learning

arXiv: https://arxiv.org/abs/1606.05579 · HTML: https://mlsanity.com/paper/1606.05579/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2016.

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

- [FitVid: Overfitting in Pixel-Level Video Prediction](https://mlsanity.com/paper/2106.13195/) (2021)
- [Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review](https://mlsanity.com/paper/2307.13125/) (2023)
- [Can self-training identify suspicious ugly duckling lesions?](https://mlsanity.com/paper/2105.07116/) (2021)
- [Machine learning of Kondo physics using variational autoencoders and symbolic regression](https://mlsanity.com/paper/2107.08013/) (2021)
- [Towards continual task learning in artificial neural networks: current approaches and insights from neuroscience](https://mlsanity.com/paper/2112.14146/) (2021)
- [Benchmarking and Enhancing Disentanglement in Concept-Residual Models](https://mlsanity.com/paper/2312.00192/) (2023)
- [Blackbird's language matrices (BLMs): a new benchmark to investigate disentangled generalisation in neural networks](https://mlsanity.com/paper/2205.10866/) (2022)
- [Physics-informed Variational Autoencoders for Improved Robustness to Environmental Factors of Variation](https://mlsanity.com/paper/2210.10418/) (2022)
- [Towards Learning Geometric Eigen-Lengths Crucial for Fitting Tasks](https://mlsanity.com/paper/2312.15610/) (2023)
- [Review of Deep Representation Learning Techniques for Brain-Computer Interfaces and Recommendations](https://mlsanity.com/paper/2405.19345/) (2024)
- [Learning Concept-Based Causal Transition and Symbolic Reasoning for Visual Planning](https://mlsanity.com/paper/2310.03325/) (2023)
- [The Construction of Reality in an AI: A Review](https://mlsanity.com/paper/2302.05448/) (2023)
- [Autoencoder-based General Purpose Representation Learning for Customer Embedding](https://mlsanity.com/paper/2402.18164/) (2024)
- [Exploring Embedding Priors in Prompt-Tuning for Improved Interpretability and Control](https://mlsanity.com/paper/2412.18582/) (2024)
- [CULT: Continual Unsupervised Learning with Typicality-Based Environment Detection](https://mlsanity.com/paper/2207.08309/) (2022)
- [A Three-Stage Bayesian Transfer Learning Framework to Improve Predictions in Data-Scarce Domains](https://mlsanity.com/paper/2510.26541/) (2025)

## Abstract (arXiv)

Automated discovery of early visual concepts from raw image data is a major open challenge in AI research. Addressing this problem, we propose an unsupervised approach for learning disentangled representations of the underlying factors of variation. We draw inspiration from neuroscience, and show how this can be achieved in an unsupervised generative model by applying the same learning pressures as have been suggested to act in the ventral visual stream in the brain. By enforcing redundancy reduction, encouraging statistical independence, and exposure to data with transform continuities analogous to those to which human infants are exposed, we obtain a variational autoencoder (VAE) framework capable of learning disentangled factors. Our approach makes few assumptions and works well across a wide variety of datasets. Furthermore, our solution has useful emergent properties, such as zero-shot inference and an intuitive understanding of "objectness".