MDNet tracking method draws great attention due to its high precision and robustness on several evaluation datasets. However, its pretrain method for feature representation and speed of feature extraction still have some limitations. In this work, we present an improved MDNet tracking algorithm to overcome the above problems. First, we propose an efficient multiple domain mechanism to train more robust deep feature. For each domain, we employ multiple classification simultaneously to identify different interested targets from multiple videos instead of original binary classification only to identify the target and background from one sequence. Second, the proposed method accelerates feature extraction procedure by using RoIAlign layer based on VGG-M network. Our algorithm, denoted by FE-MDNet, which means fast feature extraction and efficient multiple domain training for MDNet, is evaluated on OTB2015 and TrackingNet. The results show that our algorithm performs 16 times faster than MDNet with better accuracy compared to MDNet and demonstrates favorably against state-of-the-art tracking methods.

中文翻译：

---

通过快速特征提取和高效的多域训练改进 MDNet 跟踪

MDNet 跟踪方法因其在多个评估数据集上的高精度和鲁棒性而备受关注。然而，其特征表示的预训练方法和特征提取的速度仍有一定的局限性。在这项工作中，我们提出了一种改进的 MDNet 跟踪算法来克服上述问题。首先，我们提出了一种高效的多域机制来训练更强大的深度特征。对于每个域，我们同时采用多个分类来从多个视频中识别不同的感兴趣目标，而不是原始的二元分类仅从一个序列中识别目标和背景。其次，所提出的方法通过使用基于 VGG-M 网络的 RoIAlign 层来加速特征提取过程。我们的算法，用 FE-MDNet 表示，这意味着 MDNet 的快速特征提取和高效的多域训练，在 OTB2015 和 TrackingNet 上进行了评估。结果表明，与 MDNet 相比，我们的算法执行速度比 MDNet 快 16 倍，并且具有更好的准确性，并且在对抗最先进的跟踪方法方面表现出色。