Efficient Video Object Segmentation via Network Modulation
Authors:
- Linjie YangLYLinjie Yang
- Yanran WangYWYanran Wang
- Xuehan XiongXXXuehan Xiong
- Jianchao YangJYJianchao Yang
- Aggelos K. KatsaggelosAKAggelos K. Katsaggelos
- 1 June 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6499-6507
Abstract
Video object segmentation targets segmenting a specific object throughout a video sequence when given only an annotated first frame. Recent deep learning based approaches find it effective to fine-tune a general-purpose segmentation model on the annotated frame using hundreds of iterations of gradient descent. Despite the high accuracy that these methods achieve, the fine-tuning process is inefficient and fails to meet the requirements of real world applications. We propose a novel approach that uses a single forward pass to adapt the segmentation model to the appearance of a specific object. Specifically, a second meta neural network named modulator is trained to manipulate the intermediate layers of the segmentation network given limited visual and spatial information of the target object. The experiments show that our approach is 70× faster than fine-tuning approaches and achieves similar accuracy. Our model and code have been released at https://github.com/linjieyangsc/video_seg.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Learning Video Object Segmentation from Static Images2017
- Video Propagation Networks2017
- Video Segmentation via Object Flow2016
- A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation2016
- Bilateral Space Video Segmentation2016
- Fully Convolutional Networks for Semantic SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Fully Connected Object Proposals for Video Segmentation2015
- JumpCutACM Transactions on Graphics, 2015
- EpicFlow: Edge-preserving interpolation of correspondences for optical flow2015
- Video Segmentation by Tracking Many Figure-Ground Segments2013