Meta Learning with Differentiable Closed-form Solver for Fast Video Object Segmentation

@article{Liu2020MetaLW,
  title={Meta Learning with Differentiable Closed-form Solver for Fast Video Object Segmentation},
  author={Yu Liu and Lingqiao Liu and Haokui Zhang and Seyed Hamid Rezatofighi and Ian D. Reid},
  journal={2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year={2020},
  pages={8439-8446}
}
  • Yu Liu, Lingqiao Liu, I. Reid
  • Published 28 September 2019
  • Computer Science
  • 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Video object segmentation plays a vital role to many robotic tasks, beyond the satisfied accuracy, quickly adapt to the new scenario with very limited annotations and conduct a quick inference are also important. In this paper, we are specifically concerned with the task of fast segmenting all pixels of a target object in all frames, given the annotation mask in the first frame. Even when such annotation is available, this remains a challenging problem because of the changing appearance and… 

Figures and Tables from this paper

Learning What to Learn for Video Object Segmentation
TLDR
This work introduces an end-to-end trainable VOS architecture that integrates a differentiable few-shot learning module that is designed to predict a powerful parametric model of the target by minimizing a segmentation error in the first frame.
Joint Inductive and Transductive Learning for Video Object Segmentation
TLDR
This work proposes to integrate transductive and inductive learning into a unified framework to exploit the complementarity between them for accurate and robust video object segmentation and sets a series of new state-of-the-art records.
Meta-Forecasting by combining Global Deep Representations with Local Adaptation
TLDR
This work introduces a novel forecasting method, called Meta GlobalLocal Auto-Regression (Meta-GLAR), that adapts to each time series by learning in closed-form the mapping from the representations produced by a recurrent neural network (RNN) to one-step-ahead forecasts.
C LOSED - FORM S AMPLE P ROBING FOR L EARNING G ENERATIVE M ODELS IN Z ERO - SHOT L EARNING
Generative model based approaches have led to significant advances in zero-shot learning (ZSL) over the past few years. These approaches typically aim to learn a conditional generator that synthesizes

References

SHOWING 1-10 OF 50 REFERENCES
Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning
TLDR
The proposed method supports different kinds of user input such as segmentation mask in the first frame (semi-supervised scenario), or a sparse set of clicked points (interactive scenario), and reaches comparable quality to competing methods with much less interaction.
Learning Video Object Segmentation from Static Images
TLDR
It is demonstrated that highly accurate object segmentation in videos can be enabled by using a convolutional neural network (convnet) trained with static images only, and a combination of offline and online learning strategies are used.
Online Adaptation of Convolutional Neural Networks for Video Object Segmentation
TLDR
Online Adaptive Video Object Segmentation (OnAVOS) is proposed which updates the network online using training examples selected based on the confidence of the network and the spatial configuration and adds a pretraining step based on objectness, which is learned on PASCAL.
Fast and Accurate Online Video Object Segmentation via Tracking Parts
TLDR
This paper proposes a fast and accurate video object segmentation algorithm that can immediately start the segmentation process once receiving the images, and performs favorably against state-of-the-art algorithms in accuracy on the DAVIS benchmark dataset, while achieving much faster runtime performance.
Efficient Video Object Segmentation via Network Modulation
TLDR
This work proposes a novel approach that uses a single forward pass to adapt the segmentation model to the appearance of a specific object and is 70× faster than fine-tuning approaches and achieves similar accuracy.
Video Object Segmentation without Temporal Information
TLDR
Semantic One-Shot Video Object Segmentation is presented, 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).
Fast Video Object Segmentation by Reference-Guided Mask Propagation
TLDR
A deep Siamese encoder-decoder network is proposed that is designed to take advantage of mask propagation and object detection while avoiding the weaknesses of both approaches, and achieves accuracy competitive with state-of-the-art methods while running in a fraction of time compared to others.
Deep learning for detecting robotic grasps
TLDR
This work presents a two-step cascaded system with two deep networks, where the top detections from the first are re-evaluated by the second, and shows that this method improves performance on an RGBD robotic grasping dataset, and can be used to successfully execute grasps on two different robotic platforms.
CNN in MRF: Video Object Segmentation via Inference in a CNN-Based Higher-Order Spatio-Temporal MRF
TLDR
A novel CNN-embedded algorithm to perform approximate inference in the MRF, which outperforms the winning entries of the DAVIS 2017 Challenge, without resorting to model ensembling or any dedicated detectors.
Meta-learning with differentiable closed-form solvers
TLDR
The main idea is to teach a deep network to use standard machine learning tools, such as ridge regression, as part of its own internal model, enabling it to quickly adapt to novel data.
...
1
2
3
4
5
...