This paper proposes a novel active boundary loss for semantic segmentation. It can progressively encourage the alignment between predicted boundaries and ground-truth boundaries during end-to-end training, which is not explicitly enforced in commonly used cross-entropy loss. Based on the predicted boundaries detected from the segmentation results using current network parameters, we formulate the boundary alignment problem as a differentiable direction vector prediction problem to guide the movement of predicted boundaries in each iteration. Our loss is model-agnostic and can be plugged into the training of segmentation networks to improve the boundary details. Experimental results show that training with the active boundary loss can effectively improve the boundary F-score and mean Intersection-over-Union on challenging image and video object segmentation datasets.

翻译：本文建议对语义分解进行新的主动边界损失。 它可以逐步鼓励在端到端训练期间对预测边界和地面- 真实边界加以调整,而这种调整在常用的跨热带损失中没有得到明确执行。 根据利用现有网络参数从分解结果中检测到的预测边界,我们将边界调整问题作为一个不同的方向矢量预测问题,以指导每迭代中预测边界的移动。我们的损失是模型性,可以纳入分解网络的培训,以改进边界细节。实验结果显示,对实际边界损失进行的培训可以有效地改善边界的边界分界线和中度跨边界之间的差别,以便了解具有挑战性的图像和视频对象分解数据集。