Video Object Segmentation Without Temporal Information
Video Object Segmentation, and video processing in general, has been historically dominated by methods that rely on the temporal consistency and redundancy in consecutive video frames. When the temporal smoothness is suddenly broken, such as when an object is occluded, or some frames are missing in a sequence, the result of these methods can deteriorate significantly or they may not even produce any result at all. This paper explores the orthogonal approach of processing each frame independently, i.e disregarding the temporal information. In particular, it tackles the task of semi-supervised video object segmentation: the separation of an object from the background in a video, given its mask in the first frame. We present Semantic One-Shot Video Object Segmentation (OSVOS-S), based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one shot). We show that instance level semantic information, when combined effectively, can dramatically improve the results of our previous method, OSVOS. We perform experiments on two recent video segmentation databases, which show that OSVOS-S is both the fastest and most accurate method in the state of the art.
PDF Abstract
MS COCO
DAVIS
DAVIS 2017
DAVIS 2016
Referring Expressions for DAVIS 2016 & 2017
Results from the Paper
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Semi-Supervised Video Object Segmentation | DAVIS 2016 | OSVOS-S | Jaccard (Mean) | 85.6 | # 50 | |
| Jaccard (Recall) | 96.8 | # 9 | ||||
| Jaccard (Decay) | 5.5 | # 24 | ||||
| F-measure (Mean) | 87.5 | # 45 | ||||
| F-measure (Recall) | 95.9 | # 5 | ||||
| F-measure (Decay) | 8.2 | # 20 | ||||
| J&F | 86.55 | # 47 | ||||
| Semi-Supervised Video Object Segmentation | DAVIS 2017 (val) | OSVOS-S | Jaccard (Mean) | 64.7 | # 61 | |
| Jaccard (Recall) | 74.2 | # 14 | ||||
| Jaccard (Decay) | 15.1 | # 10 | ||||
| F-measure (Mean) | 71.3 | # 60 | ||||
| F-measure (Recall) | 80.7 | # 13 | ||||
| F-measure (Decay) | 18.5 | # 9 | ||||
| J&F | 68 | # 62 |
