EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow

09/20/2021
by   Yuying Hao, et al.
1

High-quality training data play a key role in image segmentation tasks. Usually, pixel-level annotations are expensive, laborious and time-consuming for the large volume of training data. To reduce labelling cost and improve segmentation quality, interactive segmentation methods have been proposed, which provide the result with just a few clicks. However, their performance does not meet the requirements of practical segmentation tasks in terms of speed and accuracy. In this work, we propose EdgeFlow, a novel architecture that fully utilizes interactive information of user clicks with edge-guided flow. Our method achieves state-of-the-art performance without any post-processing or iterative optimization scheme. Comprehensive experiments on benchmarks also demonstrate the superiority of our method. In addition, with the proposed method, we develop an efficient interactive segmentation tool for practical data annotation tasks. The source code and tool is avaliable at https://github.com/PaddlePaddle/PaddleSeg.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 8

research
10/17/2022

EISeg: An Efficient Interactive Segmentation Tool based on PaddlePaddle

In recent years, the rapid development of deep learning has brought grea...
research
01/12/2021

Rethinking Interactive Image Segmentation: Feature Space Annotation

Despite the progress of interactive image segmentation methods, high-qua...
research
04/06/2023

InterFormer: Real-time Interactive Image Segmentation

Interactive image segmentation enables annotators to efficiently perform...
research
05/07/2023

AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation

Interactive Image Segmentation (IIS) has emerged as a promising techniqu...
research
10/20/2022

SimpleClick: Interactive Image Segmentation with Simple Vision Transformers

Click-based interactive image segmentation aims at extracting objects wi...
research
07/05/2023

Interactive Image Segmentation with Cross-Modality Vision Transformers

Interactive image segmentation aims to segment the target from the backg...
research
03/31/2020

DISIR: Deep Image Segmentation with Interactive Refinement

This paper presents an interactive approach for multi-class segmentation...

Please sign up or login with your details

Forgot password? Click here to reset