CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF
Preprint
Abstract
This paper addresses the problem of video object segmentation, where the initial object mask is given in the first frame of an input video. We propose a novel spatio-temporal Markov Random Field (MRF) model defined over pixels to handle this problem. Unlike conventional MRF models, the spatial dependencies among pixels in our model are encoded by a Convolutional Neural Network (CNN). Specifically, for a given object, the probability of a labeling to a set of spatially neighboring pixels can be predicted by a CNN trained for this specific object. As a result, higher-order, richer dependencies among pixels in the set can be implicitly modeled by the CNN. With temporal dependencies established by optical flow, the resulting MRF model combines both spatial and temporal cues for tackling video object segmentation. However, performing inference in the MRF model is very difficult due to the very high-order dependencies. To this end, we propose a novel CNN-embedded algorithm to perform approximate inference in the MRF. This algorithm proceeds by alternating between a temporal fusion step and a feed-forward CNN step. When initialized with an appearance-based one-shot segmentation CNN, our model outperforms the winning entries of the DAVIS 2017 Challenge, without resorting to model ensembling or any dedicated detectors.Keywords
All Related Versions
This publication has 35 references indexed in Scilit:
- A Coupled Hidden Markov Random Field model for simultaneous face clustering and tracking in videosPattern Recognition, 2017
- Higher Order Conditional Random Fields in Deep Neural Networks2016
- Supervoxel-Consistent Foreground Propagation in Video2014
- Constrained Clustering and Its Application to Face Clustering in Videos2013
- Learning object class detectors from weakly annotated video2012
- Trajectory-Based Modeling of Human Actions with Motion Reference Points2012
- Efficient hierarchical graph-based video segmentation2010
- Robust Higher Order Potentials for Enforcing Label ConsistencyInternational Journal of Computer Vision, 2009
- TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and ContextInternational Journal of Computer Vision, 2007
- Fields of Experts: A Framework for Learning Image Priors2005