TY - JOUR AU - Wang, Chi AU - Zhang, Yunke AU - Cui, Miaomiao AU - Ren, Peiran AU - Yang, Yin AU - Xie, Xuansong AU - Hua, Xian-Sheng AU - Bao, Hujun AU - Xu, Weiwei PY - 2022/06/28 Y2 - 2024/03/29 TI - Active Boundary Loss for Semantic Segmentation JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 36 IS - 2 SE - AAAI Technical Track on Computer Vision II DO - 10.1609/aaai.v36i2.20139 UR - https://ojs.aaai.org/index.php/AAAI/article/view/20139 SP - 2397-2405 AB - 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 in to 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. ER -