# Learning Invariant World State Representations with Predictive Coding

arXiv: https://arxiv.org/abs/2207.02972 · HTML: https://mlsanity.com/paper/2207.02972/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 22 references that are in the map.
- First posted on arXiv 6 Jul 2022.

## Builds on (most cited first, 16 of 16)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [Virtual Worlds as Proxy for Multi-Object Tracking Analysis](https://mlsanity.com/paper/1605.06457/) (2016)
- [Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning](https://mlsanity.com/paper/1605.08104/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints](https://mlsanity.com/paper/1802.05522/) (2018)
- [Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos](https://mlsanity.com/paper/1811.06152/) (2018)
- [Learning Depth from Monocular Videos using Direct Methods](https://mlsanity.com/paper/1712.00175/) (2017)
- [Unsupervised Scale-consistent Depth Learning from Video](https://mlsanity.com/paper/2105.11610/) (2021)
- [LEGO: Learning Edge with Geometry all at Once by Watching Videos](https://mlsanity.com/paper/1803.05648/) (2018)
- [Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding](https://mlsanity.com/paper/1806.10556/) (2018)

## Abstract (arXiv)

Self-supervised learning methods overcome the key bottleneck for building more capable AI: limited availability of labeled data. However, one of the drawbacks of self-supervised architectures is that the representations that they learn are implicit and it is hard to extract meaningful information about the encoded world states, such as 3D structure of the visual scene encoded in a depth map. Moreover, in the visual domain such representations only rarely undergo evaluations that may be critical for downstream tasks, such as vision for autonomous cars. Herein, we propose a framework for evaluating visual representations for illumination invariance in the context of depth perception. We develop a new predictive coding-based architecture and a hybrid fully-supervised/self-supervised learning method. We propose a novel architecture that extends the predictive coding approach: PRedictive Lateral bottom-Up and top-Down Encoder-decoder Network (PreludeNet), which explicitly learns to infer and predict depth from video frames. In PreludeNet, the encoder's stack of predictive coding layers is trained in a self-supervised manner, while the predictive decoder is trained in a supervised manner to infer or predict the depth. We evaluate the robustness of our model on a new synthetic dataset, in which lighting conditions (such as overall illumination, and effect of shadows) can be be parametrically adjusted while keeping all other aspects of the world constant. PreludeNet achieves both competitive depth inference performance and next frame prediction accuracy. We also show how this new network architecture, coupled with the hybrid fully-supervised/self-supervised learning method, achieves balance between the said performance and invariance to changes in lighting. The proposed framework for evaluating visual representations can be extended to diverse task domains and invariance tests.