论文标题
朝向判别表示：在线多对象跟踪的多视图轨迹对比学习
Towards Discriminative Representation: Multi-view Trajectory Contrastive Learning for Online Multi-object Tracking
论文作者
论文摘要
判别表示对于多对象跟踪的关联步骤至关重要。最近的工作主要利用单个或相邻框架中的功能来构建度量损失并授权网络提取目标的表示。尽管此策略有效，但它无法完全利用整个轨迹中包含的信息。为此，我们提出了一种策略，即多视图轨迹对比度学习，其中每个轨迹被表示为中心向量。通过将所有向量维护在动态更新的内存库中，设计了轨迹级的对比损失，以探索整个轨迹中的框架间信息。此外，在此策略中，每个目标表示为多个自适应选择的关键点，而不是预定义的锚或中心。该设计使网络可以从同一目标的多个视图中生成更丰富的表示形式，从而可以更好地表征遮挡对象。此外，在推论阶段，开发了相似性引导的特征融合策略，以进一步提高轨迹表示的质量。已经在Motchallenge上进行了广泛的实验，以验证所提出的技术的有效性。实验结果表明，我们的方法已经超过了前面的跟踪器并建立了新的最新性能。
Discriminative representation is crucial for the association step in multi-object tracking. Recent work mainly utilizes features in single or neighboring frames for constructing metric loss and empowering networks to extract representation of targets. Although this strategy is effective, it fails to fully exploit the information contained in a whole trajectory. To this end, we propose a strategy, namely multi-view trajectory contrastive learning, in which each trajectory is represented as a center vector. By maintaining all the vectors in a dynamically updated memory bank, a trajectory-level contrastive loss is devised to explore the inter-frame information in the whole trajectories. Besides, in this strategy, each target is represented as multiple adaptively selected keypoints rather than a pre-defined anchor or center. This design allows the network to generate richer representation from multiple views of the same target, which can better characterize occluded objects. Additionally, in the inference stage, a similarity-guided feature fusion strategy is developed for further boosting the quality of the trajectory representation. Extensive experiments have been conducted on MOTChallenge to verify the effectiveness of the proposed techniques. The experimental results indicate that our method has surpassed preceding trackers and established new state-of-the-art performance.
