Video Object Segmentation with Episodic Graph Memory Networks
Authors:
Preprint
Abstract
How to make a segmentation model efficiently adapt to a specific video and to online target appearance variations are fundamentally crucial issues in the field of video object segmentation. In this work, a graph memory network is developed to address the novel idea of "learning to update the segmentation model". Specifically, we exploit an episodic memory network, organized as a fully connected graph, to store frames as nodes and capture cross-frame correlations by edges. Further, learnable controllers are embedded to ease memory reading and writing, as well as maintain a fixed memory scale. The structured, external memory design enables our model to comprehensively mine and quickly store new knowledge, even with limited visual information, and the differentiable memory controllers slowly learn an abstract method for storing useful representations in the memory and how to later use these representations for prediction, via gradient descent. In addition, the proposed graph memory network yields a neat yet principled framework, which can generalize well both one-shot and zero-shot video object segmentation tasks. Extensive experiments on four challenging benchmark datasets verify that our graph memory network is able to facilitate the adaptation of the segmentation network for case-by-case video object segmentation.Keywords
All Related Versions
This publication has 57 references indexed in Scilit:
- Region Graph Embedding Network for Zero-Shot Learning2020
- PReMVOS: Proposal-Generation, Refinement and Merging for Video Object Segmentation2019
- VideoMatch: Matching Based Video Object Segmentation2018
- Video Object Segmentation by Learning Location-Sensitive Embeddings2018
- Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection2018
- YouTube-VOS: Sequence-to-Sequence Video Object Segmentation2018
- Learning Dynamic Memory Networks for Object Tracking2018
- Learning to Segment Moving ObjectsInternational Journal of Computer Vision, 2018
- Microsoft COCO: Common Objects in Context2014
- Label propagation in video sequences2010