EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow

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.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Interactive Segmentation Berkeley EdgeFlow NoC@90 2.4 # 8
Interactive Segmentation DAVIS EdgeFlow NoC@85 4.54 # 8
NoC@90 5.77 # 9
Interactive Segmentation GrabCut EdgeFlow NoC@85 1.6 # 5
NoC@90 1.72 # 8
Interactive Segmentation PASCAL VOC EdgeFlow NoC@85 2.5 # 2