SPFTN: A self-paced fine-tuning network for segmenting objects in weakly labelled videos

Dingwen Zhang, Le Yang, Deyu Meng, Dong Xu, Junwei Han

科研成果: 书/报告/会议事项章节会议稿件同行评审

39 引用 (Scopus)

摘要

Object segmentation in weakly labelled videos is an interesting yet challenging task, which aims at learning to perform category-specific video object segmentation by only using video-level tags. Existing works in this research area might still have some limitations, e.g., lack of effective DNN-based learning frameworks, under-exploring the context information, and requiring to leverage the unstable negative video collection, which prevent them from obtaining more promising performance. To this end, we propose a novel self-paced fine-tuning network (SPFTN)-based framework, which could learn to explore the context information within the video frames and capture adequate object semantics without using the negative videos. To perform weakly supervised learning based on the deep neural network, we make the earliest effort to integrate the self-paced learning regime and the deep neural network into a unified and compatible framework, leading to the self-paced fine-tuning network. Comprehensive experiments on the large-scale YouTube-Objects and DAVIS datasets demonstrate that the proposed approach achieves superior performance as compared with other state-of-the-art methods as well as the baseline networks and models.

源语言英语
主期刊名Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
出版商Institute of Electrical and Electronics Engineers Inc.
5340-5348
页数9
ISBN(电子版)9781538604571
DOI
出版状态已出版 - 6 11月 2017
活动30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 - Honolulu, 美国
期限: 21 7月 201726 7月 2017

出版系列

姓名Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
2017-January

会议

会议30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
国家/地区美国
Honolulu
时期21/07/1726/07/17

指纹

探究 'SPFTN: A self-paced fine-tuning network for segmenting objects in weakly labelled videos' 的科研主题。它们共同构成独一无二的指纹。

引用此