论文标题
测试时间适应与培训时间概括：使用关键点估计的人类实例分割中的案例研究
Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimation
论文作者
论文摘要
我们考虑使用KePoints估算来改善给定测试图像的人类实例分割掩模质量的问题。我们比较两种替代方法。第一种方法是测试时间适应（TTA）方法，我们允许使用单个未标记的测试图像对分割网络的权重进行测试时间修改。在这种方法中，我们不假设测试时间访问被标记的源数据集。更具体地说，我们的TTA方法包括使用按键估计值作为伪标签，并将其反向传播以调整骨干权重。第二种方法是训练时间概括（TTG）方法，在该方法中，我们允许脱机访问标签的源数据集，而不能访问权重的测试时间修改。此外，我们不假定来自目标域的任何图像或知识的可用性。我们的TTG方法包括通过按键头部产生的骨干特征并将聚集矢量馈送到面罩头。通过一系列全面的消融，我们评估了这两种方法，并确定了限制TTA收益的几个因素。特别是，我们表明，在没有明显的域移位的情况下，TTA可能会受伤，而TTG仅显示出少量的增长，而对于大型域移动，TTA的增益较小，并且取决于所使用的启发式方法，而TTG的增益较大，并且对建筑选择的较大且可靠。
We consider the problem of improving the human instance segmentation mask quality for a given test image using keypoints estimation. We compare two alternative approaches. The first approach is a test-time adaptation (TTA) method, where we allow test-time modification of the segmentation network's weights using a single unlabeled test image. In this approach, we do not assume test-time access to the labeled source dataset. More specifically, our TTA method consists of using the keypoints estimates as pseudo labels and backpropagating them to adjust the backbone weights. The second approach is a training-time generalization (TTG) method, where we permit offline access to the labeled source dataset but not the test-time modification of weights. Furthermore, we do not assume the availability of any images from or knowledge about the target domain. Our TTG method consists of augmenting the backbone features with those generated by the keypoints head and feeding the aggregate vector to the mask head. Through a comprehensive set of ablations, we evaluate both approaches and identify several factors limiting the TTA gains. In particular, we show that in the absence of a significant domain shift, TTA may hurt and TTG show only a small gain in performance, whereas for a large domain shift, TTA gains are smaller and dependent on the heuristics used, while TTG gains are larger and robust to architectural choices.
