Watching the World Go By: Representation Learning from Unlabeled Videos

TL;DR

This paper introduces Video Noise Contrastive Estimation, leveraging unlabeled videos as natural augmentations to improve unsupervised image representation learning, outperforming existing methods and supervised pretraining.

Contribution

It proposes a novel method that uses unlabeled videos for unsupervised representation learning, capturing natural variations like occlusion and deformation.

Findings

Outperforms recent unsupervised image techniques.

Surpasses supervised ImageNet pretraining on various tasks.

Utilizes natural video variations for better representations.

Abstract

Recent single image unsupervised representation learning techniques show remarkable success on a variety of tasks. The basic principle in these works is instance discrimination: learning to differentiate between two augmented versions of the same image and a large batch of unrelated images. Networks learn to ignore the augmentation noise and extract semantically meaningful representations. Prior work uses artificial data augmentation techniques such as cropping, and color jitter which can only affect the image in superficial ways and are not aligned with how objects actually change e.g. occlusion, deformation, viewpoint change. In this paper, we argue that videos offer this natural augmentation for free. Videos can provide entirely new views of objects, show deformation, and even connect semantically similar but visually distinct concepts. We propose Video Noise Contrastive Estimation, a method for using unlabeled video to learn strong, transferable single image representations. We demonstrate improvements over recent unsupervised single image techniques, as well as over fully supervised ImageNet pretraining, across a variety of temporal and non-temporal tasks. Code and the Random Related Video Views dataset are available at https://www.github.com/danielgordon10/vince