当前位置: X-MOL 学术Neural Process Lett. › 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.)
Wasserstein Distance-Based Auto-Encoder Tracking
Neural Processing Letters ( IF 2.6 ) Pub Date : 2021-04-04 , DOI: 10.1007/s11063-021-10507-9
Long Xu , Ying Wei , Chenhe Dong , Chuaqiao Xu , Zhaofu Diao

Most of the existing visual object trackers are based on deep convolutional feature maps, but there have fewer works about finding new features for tracking. This paper proposes a novel tracking framework based on a full convolutional auto-encoder appearance model, which is trained by using Wasserstein distance and maximum mean discrepancy . Compared with previous works, the proposed framework has better performance in three aspects, including appearance model, update scheme, and state estimation. To address the issues of the original update scheme including poor discriminant performance under limited supervisory information, sample pollution caused by long term object occlusion, and sample importance unbalance, in this paper, a novel latent space importance weighting algorithm, a novel sample space management algorithm, and a novel IOU-based label smoothing algorithm are proposed respectively. Besides, an improved weighted loss function is adopted to address the sample imbalance issue. Finally, to improve the state estimation accuracy, the combination of Kullback-Leibler divergence and generalized intersection over union is introduced. Extensive experiments are performed on the three widely used benchmarks, and the results demonstrate the state-of-the-art performance of the proposed method. Code and models are available at https://github.com/wahahamyt/CAT.git.



中文翻译:

Wasserstein基于距离的自动编码器跟踪

大多数现有的视觉对象跟踪器都是基于深度卷积特征图的,但是有关寻找新特征进行跟踪的工作却很少。本文提出了一种基于全卷积自动编码器外观模型的新颖跟踪框架,该模型通过使用Wasserstein距离和最大均值差异进行训练。与以前的工作相比,该框架在外观模型,更新方案和状态估计三个方面都有较好的表现。为了解决原始更新方案的问题,包括监管信息有限,判别性能差,对象长期被遮挡造成的样本污染以及样本重要性不平衡,本文提出了一种新型的潜在空间重要性加权算法,一种新型的样本空间管理算法。 ,分别提出了一种新的基于IOU的标签平滑算法。此外,采用了改进的加权损失函数来解决样本不平衡问题。最后,为了提高状态估计的准确性,引入了Kullback-Leibler发散和广义相交相结合的方法。在三个广泛使用的基准上进行了广泛的实验,结果证明了该方法的最新性能。代码和模型可从https://github.com/wahahamyt/CAT.git获得。在三个广泛使用的基准上进行了广泛的实验,结果证明了该方法的最新性能。代码和模型可从https://github.com/wahahamyt/CAT.git获得。在三个广泛使用的基准上进行了广泛的实验,结果证明了该方法的最新性能。代码和模型可从https://github.com/wahahamyt/CAT.git获得。

更新日期:2021-04-04
down
wechat
bug