当前位置: X-MOL 学术Image Vis. Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Task-based parameter isolation for foreground segmentation without catastrophic forgetting using multi-scale region and edges fusion network
Image and Vision Computing ( IF 4.2 ) Pub Date : 2021-07-03 , DOI: 10.1016/j.imavis.2021.104248
Islam Osman 1 , Agwad Eltantawy 1 , Mohamed S. Shehata 1
Affiliation  

Foreground segmentation of moving objects is widely used in different computer vision applications; however, existing deep learning-based methods generally suffer from overall degraded F-measure performance. The two main sources that degrade the F-measure are under-segmentation and catastrophic forgetting. Under-segmentation is the problem of misdetecting objects' fine details. The catastrophic forgetting problem occurs when training on a large number of video sequences that leads to forgetting information learned from early video sequences. This paper proposes a novel multi-scale region and edges fusion network with task-based parameter isolation (REFNet-TBPI) to overcome these two problems. The proposed method consists of a novel multi-scale region and edges fusion network (REFNet) to capture the moving objects' boundary details by extracting regions and boundary edges of each object at different feature scales and fusing them to produce high-detailed segmented objects. REFNet is trained using a novel continual learning technique called task-based parameter isolation (TBPI) to overcome the catastrophic forgetting problem. The proposed method (REFNet-TBPI) is extensively evaluated on three benchmarks, namely CDnet2014, DAVIS2016, and SegTrack. By comparing REFNet-TBPI with current state-of-the-art methods, the proposed method outperforms the best-reported state-of-the-art by 4.4% on average.



中文翻译:

使用多尺度区域和边缘融合网络进行基于任务的前景分割参数隔离而不会发生灾难性遗忘

运动物体的前景分割被广泛应用于不同的计算机视觉应用中;然而,现有的基于深度学习的方法通常会受到整体 F-measure 性能下降的影响。降低 F-measure 的两个主要来源是欠分割和灾难性遗忘。欠分割是错误检测对象细节的问题。当对大量视频序列进行训练时会出现灾难性的遗忘问题,这会导致忘记从早期视频序列中学到的信息。本文提出了一种具有基于任务的参数隔离的新型多尺度区域和边缘融合网络(REFNet-TBPI)来克服这两个问题。所提出的方法由一个新颖的多尺度区域和边缘融合网络(REFNet)组成,用于捕捉移动物体的 通过在不同的特征尺度上提取每个对象的区域和边界边缘并将它们融合以产生高细节的分割对象来获得边界细节。REFNet 使用一种称为基于任务的参数隔离 (TBPI) 的新型持续学习技术进行训练,以克服灾难性遗忘问题。所提出的方法 (REFNet-TBPI) 在三个基准测试中得到了广泛的评估,即 CDnet2014、DAVIS2016 和 SegTrack。通过将 REFNet-TBPI 与当前最先进的方法进行比较,所提出的方法比最佳报告的最先进方法平均高出 4.4%。REFNet 使用一种称为基于任务的参数隔离 (TBPI) 的新型持续学习技术进行训练,以克服灾难性遗忘问题。所提出的方法 (REFNet-TBPI) 在三个基准测试中得到了广泛的评估,即 CDnet2014、DAVIS2016 和 SegTrack。通过将 REFNet-TBPI 与当前最先进的方法进行比较,所提出的方法比最佳报告的最先进方法平均高出 4.4%。REFNet 使用一种称为基于任务的参数隔离 (TBPI) 的新型持续学习技术进行训练,以克服灾难性遗忘问题。所提出的方法 (REFNet-TBPI) 在三个基准测试中得到了广泛的评估,即 CDnet2014、DAVIS2016 和 SegTrack。通过将 REFNet-TBPI 与当前最先进的方法进行比较,所提出的方法比最佳报告的最先进方法平均高出 4.4%。

更新日期:2021-07-09
down
wechat
bug