论文标题
嘈杂的边界：半监督实例分割的柠檬或柠檬水？
Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?
论文作者
论文摘要
当前实例分割方法在很大程度上依赖于像素级注释的图像。获取此类完全注销的图像的巨大成本限制了数据集量表并限制了性能。在本文中，我们正式解决了半监督实例分割，其中使用未标记的图像来提高性能。我们通过分配像素级伪标签来构建半监视实例分割的框架。在此框架下，我们指出，与伪标签相关的嘈杂边界是双边的。我们建议以统一的方式利用和抵抗它们：1）应对嘈杂边界的负面影响，我们通过利用低分辨率特征提出一个耐噪声的面具头。 2）为了增强积极影响，我们引入了一个保留边界的地图，以学习与边界相关区域内的详细信息。我们通过广泛的实验评估我们的方法。它的行为极为巨大，超过监督基线的利润率很大，城市景观的6％以上，可可的基线超过7％，而BDD100K的基线占4％。在CityScapes上，我们的方法仅利用30％标记的图像来实现可比的性能。
Current instance segmentation methods rely heavily on pixel-level annotated images. The huge cost to obtain such fully-annotated images restricts the dataset scale and limits the performance. In this paper, we formally address semi-supervised instance segmentation, where unlabeled images are employed to boost the performance. We construct a framework for semi-supervised instance segmentation by assigning pixel-level pseudo labels. Under this framework, we point out that noisy boundaries associated with pseudo labels are double-edged. We propose to exploit and resist them in a unified manner simultaneously: 1) To combat the negative effects of noisy boundaries, we propose a noise-tolerant mask head by leveraging low-resolution features. 2) To enhance the positive impacts, we introduce a boundary-preserving map for learning detailed information within boundary-relevant regions. We evaluate our approach by extensive experiments. It behaves extraordinarily, outperforming the supervised baseline by a large margin, more than 6% on Cityscapes, 7% on COCO and 4.5% on BDD100k. On Cityscapes, our method achieves comparable performance by utilizing only 30% labeled images.
