论文标题
通过注意检索进行准确的像素对象跟踪
Towards Accurate Pixel-wise Object Tracking by Attention Retrieval
论文作者
论文摘要
对象跟踪中目标的编码最近从粗边界框移动到细粒细分图。重新审视了能够在跟踪过程中预测掩模的事实上的实时方法，我们观察到它们通常从骨干网络上为分割分割光线分支。虽然有效，但直接融合了主链特征而没有考虑背景杂波的负面影响，往往会引入错误的阴性预测，从而落后于分割的精度。为了减轻此问题，我们提出了一个注意检索网络（ARN），以对骨干特征执行软空间约束。我们首先在起始框架中使用地面掩码构建了一个查找桌（LUT），然后检索LUT以获取空间约束的注意力图。此外，我们引入了多分辨率的多阶段分割网络（MMS），以通过重复预测的掩码过滤骨干链特征来进一步削弱背景杂物的影响。我们的方法在以40 fps运行时，在最近的像素对象跟踪基准dot2020上为最新的对象跟踪。值得注意的是，拟议的模型分别超过了Siammask，分别在Dot2020，Davis2016和Davis2017上超过11.7/4.2/5.5分。我们将在https://github.com/researchmm/trackit上发布代码。
The encoding of the target in object tracking moves from the coarse bounding-box to fine-grained segmentation map recently. Revisiting de facto real-time approaches that are capable of predicting mask during tracking, we observed that they usually fork a light branch from the backbone network for segmentation. Although efficient, directly fusing backbone features without considering the negative influence of background clutter tends to introduce false-negative predictions, lagging the segmentation accuracy. To mitigate this problem, we propose an attention retrieval network (ARN) to perform soft spatial constraints on backbone features. We first build a look-up-table (LUT) with the ground-truth mask in the starting frame, and then retrieves the LUT to obtain an attention map for spatial constraints. Moreover, we introduce a multi-resolution multi-stage segmentation network (MMS) to further weaken the influence of background clutter by reusing the predicted mask to filter backbone features. Our approach set a new state-of-the-art on recent pixel-wise object tracking benchmark VOT2020 while running at 40 fps. Notably, the proposed model surpasses SiamMask by 11.7/4.2/5.5 points on VOT2020, DAVIS2016, and DAVIS2017, respectively. We will release our code at https://github.com/researchmm/TracKit.
