Motion is a powerful cue that humans use to detect and segment visual objects.

Segmentation, the task of delineating and isolating distinct objects, is a fundamental problem in computer vision. Much of the current approaches are supervised, relying on expensive manual annotations.

Di Lin is the corresponding author of this paper.

Extended " T able 2" in submitted paper. Extended " T able 3" in submitted paper. We thank reviewers for their comments, and will carefully revise paper considering these comments. Q1 (R1): References and comparison with a baseline that learns embeddings only through a standard convnet. In Tab.2 of this rebuttal, the state-of-the-art method of AISI [7] also depends on We will give more details of these compared methods in paper for clarity.

Neural Information Processing Systems http://nips.cc/

Recently,there has been agrowing interest in developing saliencymethods that providevisualexplanations ofnetworkpredictions. Still,theusability ofexisting methods is limited to image classification models. To overcome this limitation, we extend the existing approaches to generategrid saliencies, which provide spatially coherent visualexplanations for(pixel-level)denseprediction networks.