Abstract
Existing deep trackers are typically trained with largescale video frames with annotated bounding boxes. However, these bounding boxes are expensive and time-consuming to annotate, in particular for large scale datasets. In this paper, we propose to learn tracking representations from single point annotations (i.e., 4.5x faster to annotate than the traditional bounding box) in a weakly supervised manner. Specifically, we propose a soft contrastive learning (SoCL) framework that incorporates target objectness prior into end-to-end contrastive learning. Our SoCL consists of adaptive positive and negative sample generation, which is memory-efficient and effective for learning tracking representations. We apply the learned representation of SoCL to visual tracking and show that our method can 1) achieve better performance than the fully supervised baseline trained with box annotations under the same annotation time cost; 2) achieve comparable performance of the fully supervised baseline by using the same number of training frames and meanwhile reducing annotation time cost by 78% and total fees by 85%; 3) be robust to annotation noise.
Abstract (translated)
现有的深跟踪器通常使用带有注释边界框的大规模视频帧进行训练。然而，这些边界框通常是昂贵且耗时的，尤其是在大规模数据集上。在本文中，我们提出了一种弱监督方式从单点注释中学习跟踪表示。具体来说，我们提出了一种软对比学习（SoCL）框架，该框架将目标对象的 prior 融入了端到端的对比学习。我们的 SoCL 包括自适应的正负样本生成，这种方法具有内存效率和有效的学习跟踪表示。我们将 SoCL 学习到的表示应用于视觉跟踪，并证明了我们的方法可以在与相同注释时间成本下实现比完全监督基准更好的性能，2）通过使用相同的训练帧数量并减少78%的注释时间成本实现与完全监督基准相当的性能，3）对注释噪声具有鲁棒性。
URL
https://arxiv.org/abs/2404.09504
