Active Boundary Loss for Semantic Segmentation
This work addresses the problem of improving boundary detail in semantic segmentation for computer vision tasks, offering an incremental improvement to existing methods.
This paper introduces an active boundary loss to improve semantic segmentation by explicitly aligning predicted boundaries with ground-truth boundaries. This loss function, which is model-agnostic, has been shown to enhance boundary F-score and mean Intersection-over-Union on various image and video object segmentation datasets.
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.