In this paper, we introduce a data-efficient instance segmentation method we used in the 2021 VIPriors Instance Segmentation Challenge. Our solution is a modified version of Swin Transformer, based on the mmdetection which is a powerful toolbox. To solve the problem of lack of data, we utilize data augmentation including random flip and multiscale training to train our model. During inference, multiscale fusion is used to boost the performance. We only use a single GPU during the whole training and testing stages. In the end, our team achieved the result of 0.366 for AP@0.50:0.95 on the test set, which is competitive with other top-ranking methods while only one GPU is used. Besides, our method achieved the AP@0.50:0.95 (medium) of 0.592, which ranks second among all contestants. In the end, our team ranked third among all the contestants, as announced by the organizers.

翻译：在本文中,我们引入了一种数据高效实例分解方法,我们在2021年VIPRPR Creative Creative Creative 挑战中使用了这种方法。 我们的解决方案是基于一个强大的工具箱, 以毫米探测器为基础, 修改 Swin 变换器的版本。 为了解决数据缺乏的问题, 我们使用数据增强, 包括随机翻转和多尺度的培训来培训我们的模型。 在推论过程中, 多尺度的聚合用于提升性能。 我们只在整个培训和测试阶段使用单一的 GPU 。 最后, 我们的团队在测试组上取得了0. 366 AP@ 0. 50: 0. 95 的结果, 测试组与其他顶级方法相比具有竞争力, 而只使用了一个 GPU 。 此外, 我们的方法达到了0. 592 的 AP@ 0. 50: 0. 95 (中型), 在所有参赛者中排名第二。 最后, 我们的团队在所有参赛者中排第三, 正如组织者所宣布的那样, 。