# UCP-Net: Unstructured Contour Points for Instance Segmentation Source: [UCP-Net: Unstructured Contour Points for Instance Segmentation]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:33:54.629Z Authors: Camille Dupont, Yanis Ouakrim, Quoc Cuong Pham Published: 2021-09-15T22:03:37.000Z ## Abstract 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. In this paper, we propose a novel approach to interactive segmentation based on unconstrained contour clicks for initial segmentation and segmentation refinement. Our 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). ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Interactive Instance Segmentation on COCO (MVal)](): Interactive Instance Segmentation; COCO (MVal); NoC @ 85%: 2. - [Interactive Instance Segmentation on Berkeley (test)](): Interactive Instance Segmentation; Berkeley (test); NoC @ 90%: 2.7. - [Interactive Instance Segmentation on SBD 1 (test)](): Interactive Instance Segmentation; SBD 1 (test); NoC @ 85%: 2.73. - [Interactive Instance Segmentation on GrabCut (test)](): Interactive Instance Segmentation; GrabCut (test); NoC @ 90%: 2.76. ## Original sources and implementation [Original paper]() [PDF]()