UCP-Net: Unstructured Contour Points for Instance Segmentation

TL;DR

UCP-Net introduces a class-agnostic interactive segmentation method using unconstrained contour clicks, achieving high accuracy with fewer user interactions on standard datasets.

Contribution

The paper presents a novel approach leveraging unstructured contour points for efficient, accurate, and class-agnostic interactive segmentation.

Findings

Achieves IoU > 85% with fewer interactions than existing methods.

Works effectively across multiple popular segmentation datasets.

Provides a simple and intuitive user interaction mechanism.

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).