Papers › UCP-Net: Unstructured Contour Points for Instance Segmentation

UCP-Net: Unstructured Contour Points for Instance Segmentation

15 Sep 2021arXiv:2109.07592archive 2025-07-28

Camille Dupont, Yanis Ouakrim, Quoc Cuong Pham

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).

Paper PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Instance Segmentation Interactive Segmentation Segmentation Semantic Segmentation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Interactive Segmentation	Berkeley	UCP-Net	NoC@90	2.70	#9 of 14	Archive leaderboard	report
Interactive Segmentation	GrabCut	UCP-Net	NoC@85	2	#11 of 18	Archive leaderboard	report
Interactive Segmentation	GrabCut	UCP-Net	NoC@90	2.76	#11 of 18	Archive leaderboard	report
Interactive Segmentation	SBD	UCP-Net	NoC@85	2.73	#3 of 14	Archive leaderboard	report
Interactive Segmentation	SBD	UCP-Net	NoC@90	5.00	#3 of 14	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 Convolution Average Pooling Concatenated Skip Connection Convolution Dense Connections Depthwise Convolution Depthwise Separable Convolution Global Average Pooling Max Pooling Pointwise Convolution ReLU Residual Connection Softmax U-Net

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections