We propose a novel data augmentation method `GridMask' in this paper. It utilizes information removal to achieve state-of-the-art results in a variety of computer vision tasks. We analyze the requirement of information dropping. Then we show limitation of existing information dropping algorithms and propose our structured method, which is simple and yet very effective. It is based on the deletion of regions of the input image. Our extensive experiments show that our method outperforms the latest AutoAugment, which is way more computationally expensive due to the use of reinforcement learning to find the best policies. On the ImageNet dataset for recognition, COCO2017 object detection, and on Cityscapes dataset for semantic segmentation, our method all notably improves performance over baselines. The extensive experiments manifest the effectiveness and generality of the new method.
翻译:我们在本文中建议采用新的数据增强方法“ GridMask ” 。 它使用信息移除来实现计算机各种视觉任务的最新结果。 我们分析信息下降的要求。 然后我们展示现有信息下降算法的限制, 并提出我们的结构化方法, 这种方法简单而有效, 以删除输入图像的区域为基础。 我们的广泛实验显示, 我们的方法超过了最新的自动增强方法, 由于使用强化学习来寻找最佳政策, 在计算上成本更高。 在图像网络数据集上, COCO2017天天体探测, 和用于语义分解的城景数据集, 我们的方法都显著改善了基线的性能。 广泛的实验显示了新方法的有效性和一般性。