Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning

TL;DR

This paper introduces PredNet, a predictive neural network inspired by neuroscience, that learns to predict future video frames, enabling unsupervised learning of object and scene structure useful for recognition and control tasks.

Contribution

The paper presents PredNet, a novel predictive coding-based neural network architecture for unsupervised video prediction and representation learning, demonstrating its effectiveness on synthetic and real-world videos.

Findings

PredNet accurately predicts future frames in synthetic videos.

Learned representations support object recognition with fewer views.

Model scales to complex natural videos and estimates steering angles.

Abstract

While great strides have been made in using deep learning algorithms to solve supervised learning tasks, the problem of unsupervised learning - leveraging unlabeled examples to learn about the structure of a domain - remains a difficult unsolved challenge. Here, we explore prediction of future frames in a video sequence as an unsupervised learning rule for learning about the structure of the visual world. We describe a predictive neural network ("PredNet") architecture that is inspired by the concept of "predictive coding" from the neuroscience literature. These networks learn to predict future frames in a video sequence, with each layer in the network making local predictions and only forwarding deviations from those predictions to subsequent network layers. We show that these networks are able to robustly learn to predict the movement of synthetic (rendered) objects, and that in doing so, the networks learn internal representations that are useful for decoding latent object parameters (e.g. pose) that support object recognition with fewer training views. We also show that these networks can scale to complex natural image streams (car-mounted camera videos), capturing key aspects of both egocentric movement and the movement of objects in the visual scene, and the representation learned in this setting is useful for estimating the steering angle. Altogether, these results suggest that prediction represents a powerful framework for unsupervised learning, allowing for implicit learning of object and scene structure.