papers AI Learner
The Github is limit! Click to go to the new site.

Unsupervised Learning from Video with Deep Neural Embeddings

2019-05-28
Chengxu Zhuang, Alex Andonian, Daniel Yamins

Abstract

Because of the rich dynamical structure of videos and their ubiquity in everyday life, it is a natural idea that video data could serve as a powerful unsupervised learning signal for training visual representations in deep neural networks. However, instantiating this idea, especially at large scale, has remained a significant artificial intelligence challenge. Here we present the Video Instance Embedding (VIE) framework, which extends powerful recent unsupervised loss functions for learning deep nonlinear embeddings to multi-stream temporal processing architectures on large-scale video datasets. We show that VIE-trained networks substantially advance the state of the art in unsupervised learning from video datastreams, both for action recognition in the Kinetics dataset, and object recognition in the ImageNet dataset. We show that a hybrid model with both static and dynamic processing pathways is optimal for both transfer tasks, and provide analyses indicating how the pathways differ. Taken in context, our results suggest that deep neural embeddings are a promising approach to unsupervised visual learning across a wide variety of domains.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1905.11954

PDF

https://arxiv.org/pdf/1905.11954


Similar Posts

Comments