论文标题
专注：关于监督语义分割变压器对新域中新对象的概括能力
AttEntropy: On the Generalization Ability of Supervised Semantic Segmentation Transformers to New Objects in New Domains
论文作者
论文摘要
除了令人印象深刻的性能外，视觉变形金刚还表现出了非凡的能力来编码未经培训的信息。例如，即使网络仅接受了图像识别训练，此信息也可用于执行分割或单视深度估计。我们表明，当以有监督的方式对语义细分的明确训练变压器以针对一组类别进行培训时，也会发生类似的现象：一旦接受过培训，它们即使在培训集中缺少类别也提供了有价值的信息。这些信息可用于从这些从未见过的域中的物体中分割出与道路障碍物，停放在码头，月球岩石和海上危害的飞机不同的域中。
In addition to impressive performance, vision transformers have demonstrated remarkable abilities to encode information they were not trained to extract. For example, this information can be used to perform segmentation or single-view depth estimation even though the networks were only trained for image recognition. We show that a similar phenomenon occurs when explicitly training transformers for semantic segmentation in a supervised manner for a set of categories: Once trained, they provide valuable information even about categories absent from the training set. This information can be used to segment objects from these never-seen-before classes in domains as varied as road obstacles, aircraft parked at a terminal, lunar rocks, and maritime hazards.
