arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.07504cs.CVcs.LG
收藏

通过轻量级时间不确定性估计改进视频实例分割

Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates

University of Wuppertal \& ICMD

Kira Maag, Matthias Rottmann, Serin Varghese, Fabian Hueger, Peter Schlicht, Hanno Gottschalk

AI总结:

本文提出一种基于时间动态模型的轻量级方法,用于改进视频实例分割的不确定性估计和假阳性检测,提升分割性能。

摘要:

实例分割与神经网络密切相关,是环境感知中的关键任务。在许多研究中,观察到神经网络可以以高置信度预测假阳性实例,而真正阳性实例则以低置信度预测。因此,准确建模神经网络的不确定性对于防止安全问题和促进可解释性至关重要。在自动化驾驶等应用中,神经网络的可靠性尤为重要。本文提出了一种时间动态方法,用于建模实例分割网络的不确定性,并将其应用于假阳性检测以及预测质量的估计。在线应用中图像序列的可用性允许在多个帧上跟踪实例。基于实例的历史形状和不确定性信息,我们构建了时间实例聚合度量。后者被用作后处理模型的输入,以实例级交并比的方式估计预测质量。所提出的方法仅需要一个容易训练的神经网络(可能在单帧上运行)和视频序列输入。在我们的实验中,我们进一步通过用传统对象检测的分数值替换所提出的方法,从而提高实例分割网络的整体性能。

英文摘要:

Instance segmentation with neural networks is an essential task in environment perception. In many works, it has been observed that neural networks can predict false positive instances with high confidence values and true positives with low ones. Thus, it is important to accurately model the uncertainties of neural networks in order to prevent safety issues and foster interpretability. In applications such as automated driving, the reliability of neural networks is of highest interest. In this paper, we present a time-dynamic approach to model uncertainties of instance segmentation networks and apply this to the detection of false positives as well as the estimation of prediction quality. The availability of image sequences in online applications allows for tracking instances over multiple frames. Based on an instances history of shape and uncertainty information, we construct temporal instance-wise aggregated metrics. The latter are used as input to post-processing models that estimate the prediction quality in terms of instance-wise intersection over union. The proposed method only requires a readily trained neural network (that may operate on single frames) and video sequence input. In our experiments, we further demonstrate the use of the proposed method by replacing the traditional score value from object detection and thereby improving the overall performance of the instance segmentation network.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑