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

Unsupervised Moving Object Detection via Contextual Information Separation

2019-01-10
Yanchao Yang, Antonio Loquercio, Davide Scaramuzza, Stefano Soatto

Abstract

We propose an adversarial contextual model for detecting moving objects in images. A deep neural network is trained to predict the optical flow in a region using information from everywhere else but that region (context), while another network attempts to make such context as uninformative as possible. The result is a model where hypotheses naturally compete with no need for explicit regularization or hyper-parameter tuning. Although our method requires no supervision whatsoever, it outperforms several methods that are pre-trained on large annotated datasets. Our model can be thought of as a generalization of classical variational generative region-based segmentation, but in a way that avoids explicit regularization or solution of partial differential equations at run-time.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1901.03360

PDF

http://arxiv.org/pdf/1901.03360


Similar Posts

Comments