当前位置: X-MOL 学术IEEE Trans. Pattern Anal. Mach. Intell. › 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.)
Online Meta Adaptation for Fast Video Object Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence ( IF 20.8 ) Pub Date : 1-14-2019 , DOI: 10.1109/tpami.2018.2890659
Huaxin Xiao , Bingyi Kang , Yu Liu , Maojun Zhang , Jiashi Feng

Conventional deep neural networks based video object segmentation (VOS) methods are dominated by heavily fine-tuning a segmentation model on the first frame of a given video, which is time-consuming and inefficient. In this paper, we propose a novel method which rapidly adapts a base segmentation model to new video sequences with only a couple of model-update iterations, without sacrificing performance. Such attractive efficiency benefits from the meta-learning paradigm which leads to a meta-segmentation model and a novel continuous learning approach which enables online adaptation of the segmentation model. Concretely, we train a meta-learner on multiple VOS tasks such that the meta model can capture their common knowledge and gains the ability to fast adapt the segmentation model to new video sequences. Furthermore, to deal with unique challenges of VOS tasks from temporal variations in the video, e.g., object motion and appearance changes, we propose a principled online adaptation approach that continuously adapts the segmentation model across video frames by exploiting temporal context effectively, providing robustness to annoying temporal variations. Integrating the meta-learner with the online adaptation approach, the proposed VOS model achieves competitive performance against the state-of-the-arts and moreover provides faster per-frame processing speed.

中文翻译:


用于快速视频对象分割的在线元适应



传统的基于深度神经网络的视频对象分割(VOS)方法主要是在给定视频的第一帧上对分割模型进行大量微调,这是耗时且低效的。在本文中,我们提出了一种新颖的方法,只需几次模型更新迭代即可快速使基本分割模型适应新的视频序列,而不会牺牲性能。这种有吸引力的效率得益于元学习范式,它产生了元分割模型和一种新颖的连续学习方法,可以在线适应分割模型。具体来说,我们在多个 VOS 任务上训练元学习器,以便元模型可以捕获它们的共同知识,并获得快速使分割模型适应新视频序列的能力。此外,为了应对视频中时间变化(例如对象运动和外观变化)带来的 VOS 任务的独特挑战,我们提出了一种有原则的在线适应方法,该方法通过有效利用时间上下文来持续适应跨视频帧的分割模型,从而为烦人的时间变化。将元学习器与在线适应方法相结合,所提出的 VOS 模型实现了与最先进技术相比的竞争性能,而且提供了更快的每帧处理速度。
更新日期:2024-08-22
down
wechat
bug