CNN in MRF: Video Object Segmentation via Inference in a CNN-Based Higher-Order Spatio-Temporal MRF

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 spatiotemporal Markov Random Field (MRF) model defined over pixels to handle this problem. Unlike conventional MRF models, the spatial depend...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition S. 5977 - 5986
Hauptverfasser: Bao, Linchao, Wu, Baoyuan, Liu, Wei
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2018
Schlagworte:
Approximation algorithms
Benchmark testing
Inference algorithms
Labeling
Object segmentation
Random variables
Task analysis
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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 spatiotemporal 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.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00626