Open AccessPosted Content
One-Shot Video Object Segmentation
Sergi Caelles,Kevis-Kokitsi Maninis,Jordi Pont-Tuset,Laura Leal-Taixé,Daniel Cremers,Luc Van Gool +5 more
TLDR
One-shot video object segmentation (OSVOS) as mentioned in this paper is 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.Abstract:
This paper tackles the task of semi-supervised video object segmentation, i.e., the separation of an object from the background in a video, given the mask of the first frame. We present One-Shot Video Object Segmentation (OSVOS), 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). Although all frames are processed independently, the results are temporally coherent and stable. We perform experiments on two annotated video segmentation databases, which show that OSVOS is fast and improves the state of the art by a significant margin (79.8% vs 68.0%).read more
Citations
More filters
Proceedings ArticleDOI
Enhancing Boundary for Video Object Segmentation
Qi Zhang,Xiaoqiang Lu,Yuan Yuan +2 more
TL;DR: Experimental results show that by considering supervoxel with spatial details, the proposed method can achieve impressive performance for video object segmentation through enhancing object boundary.
Journal ArticleDOI
Efficient Real-Time Tracking of Satellite Components Based on Frame Matching
TL;DR: Wang et al. as discussed by the authors proposed an efficient satellite component tracking technique based on Rethinking Space-Time Networks with Improved Memory Coverage (STCN), which reduces the contribution of background region in feature matching and enhances the robustness of the model in low illumination environment.
Book ChapterDOI
Aggregating Spatio-temporal Context for Video Object Segmentation
TL;DR: This work exploits the spatio-temporal relationship among image regions by modelling the dependencies among the corresponding visual features with a spatio -temporal RNN to aggregate spatio, temporal, and spatial contextual information for video object segmentation.
Posted ContentDOI
Learning Memory Propagation And Matching For Semi-Supervised Video Object Segmentation
TL;DR: A memory propagation and matching (MPM) method is proposed, combining the propagation- based method and matching-based method simultaneously, to reduce some wrong matching and maintain the consistency between adjacent frames and make the model more robust to occlusion and object disappearance and reproduction.
CLIP-S$^4$: Language-Guided Self-Supervised Semantic Segmentation
TL;DR: Li et al. as discussed by the authors proposed a self-supervised pixel representation learning and vision-language models to enable various semantic segmentation tasks (e.g., unsupervised, transfer learning, language-driven segmentation) without any human annotations and unknown class information.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Book ChapterDOI
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Posted Content
Deep Residual Learning for Image Recognition
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.