Zero-Episode Few-Shot Contrastive Predictive Coding: Solving intelligence tests without prior training

TL;DR

This paper introduces a data-efficient, contrastive predictive coding approach that solves sequence completion intelligence tests and other tasks with minimal examples, bypassing the need for generative models.

Contribution

The paper presents a novel one-dimensional Markov Contrastive Predictive Coding model that efficiently solves sequence prediction and anomaly detection tasks without prior training.

Findings

M-CPC_1D solves sequence completion tests with only five examples.

The model effectively detects anomalies without prior training.

It can predict stochastic movements in videos successfully.

Abstract

Video prediction models often combine three components: an encoder from pixel space to a small latent space, a latent space prediction model, and a generative model back to pixel space. However, the large and unpredictable pixel space makes training such models difficult, requiring many training examples. We argue that finding a predictive latent variable and using it to evaluate the consistency of a future image enables data-efficient predictions because it precludes the necessity of a generative model training. To demonstrate it, we created sequence completion intelligence tests in which the task is to identify a predictably changing feature in a sequence of images and use this prediction to select the subsequent image. We show that a one-dimensional Markov Contrastive Predictive Coding (M-CPC_1D) model solves these tests efficiently, with only five examples. Finally, we demonstrate the usefulness of M-CPC_1D in solving two tasks without prior training: anomaly detection and stochastic movement video prediction.