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.

提出了一种基于对抗上下文模型的无监督学习方法，在使用深度神经网络预测图像中某个区域的光流时利用其他区域的上下文信息，并通过优化上下文信息使得变量之间自然地竞争而不需要显式的正则化或超参数调整，该方法能够在无需任何监督的情况下胜过多种预训练于大型标注数据集的方法，可看作是经典区域分割的广义推广。