UCP-Net: an unstructured Contour Points for Instance Segmentation

The goal of interactive segmentation is to assist users in producing segmentation masks as fast and as accurately as possible. Interactions have to be simple and intuitive and the number of interactions required to produce a satisfactory segmentation mask should be as low as possible. A novel approach to interactive segmentation based on unconstrained contour clicks for initial segmentation and segmentation refinement is introduced in Dupont, C., Ouakrim, Y., & Pham, Q. C. (2021). UCP-Net: Unstructured Contour Points for Instance Segmentation. arXiv preprint arXiv:2109.07592.

The method is class-agnostic and produces accurate segmentation masks (IoU >85%) for a lower number of user interactions than state-of-the-art methods on popular segmentation datasets (COCO MVal, SBD and Berkeley).

UCP-Net will be integrated soon as a new Pixano feature for smart segmentation annotation.