发表机构
Linköping University; Saab; Zenseact（林雪平大学; 萨博公司; Zenseact公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对视觉实例分割中物体形状不受约束变化的难题，提出训练神经网络计算距离图以近似带符号距离函数（SDF）的方法，在COCO数据集上较YOLACT实现了更高的前景IoU，是实例分割的有前景研究方向。
AI 中文摘要
视觉实例分割是一项具有挑战性的问题，若感兴趣的物体形状不受约束地变化，难度会进一步提升。部分物体可通过矩形很好地描述，但情况并非总是如此，例如绳索这类细长物体。基于锚框的方法会将预定义的边界框分类为负样本或正样本，因此可处理的形状集合有限。定义能适配所有可能形状的锚框会导致先验框数量不可行。本文探索了一种不同的方法，提出训练神经网络以计算不同方向上的距离图，该网络在每个像素处被训练以预测给定方向上到最近物体轮廓的距离。通过对距离图进行池化，我们得到带符号距离函数（SDF）的近似值，随后可对SDF进行阈值处理以获得前景-背景分割。我们将该分割与最先进的实例分割方法YOLACT得到的前景分割进行比较，在COCO数据集上，我们的分割在前景交并比（IoU）方面表现出更高的性能。然而，尽管距离图包含各个实例的信息，但将其映射到完整的实例分割并非易事。我们仍然认为，这一思路作为实例分割的研究方向颇具前景，因为它能更好地捕捉现实世界中存在的不同形状。
英文摘要
Visual instance segmentation is a challenging problem and becomes even more difficult if objects of interest varies unconstrained in shape. Some objects are well described by a rectangle, however, this is hardly always the case. Consider for instance long, slender objects such as ropes. Anchor-based approaches classify predefined bounding boxes as either negative or positive and thus provide a limited set of shapes that can be handled. Defining anchor-boxes that fit well to all possible shapes leads to an infeasible number of prior boxes. We explore a different approach and propose to train a neural network to compute distance maps along different directions. The network is trained at each pixel to predict the distance to the closest object contour in a given direction. By pooling the distance maps we obtain an approximation to the signed distance function (SDF). The SDF may then be thresholded in order to obtain a foreground-background segmentation. We compare this segmentation to foreground segmentations obtained from the state-of-the-art instance segmentation method YOLACT. On the COCO dataset, our segmentation yields a higher performance in terms of foreground intersection over union (IoU). However, while the distance maps contain information on the individual instances, it is not straightforward to map them to the full instance segmentation. We still believe that this idea is a promising research direction for instance segmentation, as it better captures the different shapes found in the real world.
