Instance segmentation requires a large number of training samples to achieve satisfactory performance and benefits from proper data augmentation. To enlarge the training set and increase the diversity, previous methods have investigated using data annotation from other domain (e.g. bbox, point) in a weakly supervised mechanism. In this paper, we present a simple, efficient and effective method to augment the training set using the existing instance mask annotations. Exploiting the pixel redundancy of the background, we are able to improve the performance of Mask R-CNN for 1.7 mAP on COCO dataset and 3.3 mAP on Pascal VOC dataset by simply introducing random jittering to objects. Furthermore, we propose a location probability map based approach to explore the feasible locations that objects can be placed based on local appearance similarity. With the guidance of such map, we boost the performance of R101-Mask R-CNN on instance segmentation from 35.7 mAP to 37.9 mAP without modifying the backbone or network structure. Our method is simple to implement and does not increase the computational complexity. It can be integrated into the training pipeline of any instance segmentation model without affecting the training and inference efficiency. Our code and models have been released at https://github.com/GothicAi/InstaBoost
翻译:为了扩大培训组,增加多样性,以前的方法是在一个薄弱的监督下机制中使用来自其他领域(例如bbox,点)的数据注释进行调查;在本文件中,我们提出了一个简单、高效和有效的方法,用现有实例掩码说明来扩大培训组;利用背景的像素冗余,我们能够改进Mask R-CN的性能,使其在COCO数据集上1.7 mAP的1.7 mAP和关于Pascal VOC数据集的3.3 mAP的性能,仅对物体进行随机抽取。此外,我们提出基于地点概率图的方法,以探讨物体可以在当地外观相似性的基础上放置的可行地点。在这种地图的指导下,我们将R101-Mask R-CN的性能从35.7 mAP提高到37.9 mAP,但不改变主干线或网络结构。我们的方法简单易实施,也不增加计算的复杂性。我们可以在任何实例分割模型中结合,而不影响MA/GO的节能模型。