2020 · 16 citations · 21 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionImage SegmentationInstance SegmentationSemantic SegmentationVideo AnalysisAccuracyBenchmark DatasetsMatchingReal-time ProcessingReal-time SegmentationSegmentationSemi-supervised SegmentationVideo Object
Though recent methods on semi-supervised video object segmentation (VOS) have achieved an appreciable improvement of segmentation accuracy, it is still hard to get an adequate speed-accuracy balance when facing real-world application scenarios. In this work, we propose Discriminative Matching for real-time Video Object Segmentation (DMVOS), a real-time VOS framework with high-accuracy to fill this gap. Based on the matching mechanism, our framework introduces discriminative information through the Isometric Correlation module and the Instance Center Offset module. Specifically, the isometric correlation module learns a pixel-level similarity map with semantic discriminability, and the instance center offset module is applied to exploit the instance-level spatial discriminability. Experiments on two benchmark datasets show that our model achieves state-of-the-art performance with extremely fast speed, for example, J&F of 87.8% on DAVIS-2016 validation set with 35 milliseconds per frame.
21
Xiaolong Wang, Ross Girshick, Abhinav Gupta et al. · 2018 · 11.2K citations
A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation
Federico Perazzi, Jordi Pont-Tuset, Brian McWilliams et al. · 2016 · 2K citations
Hierarchical Saliency Detection
Qiong Yan, Li Xu, Jianping Shi et al. · 2013 · 1.8K citations
Fast Online Object Tracking and Segmentation: A Unifying Approach
Qiang Wang, Li Zhang, Luca Bertinetto et al. · 2019 · 1.5K citations