Getting to 99% Accuracy in Interactive Segmentation
Interactive object cutout tools are the cornerstone of the image editing workflow. Recent deep-learning based interactive segmentation algorithms have made significant progress in handling complex images and rough binary selections can typically be obtained with just a few clicks. Yet, deep learning techniques tend to plateau once this rough selection has been reached. In this work, we interpret this plateau as the inability of current algorithms to sufficiently leverage each user interaction and also as the limitations of current training/testing datasets. We propose a novel interactive architecture and a novel training scheme that are both tailored to better exploit the user workflow. We also show that significant improvements can be further gained by introducing a synthetic training dataset that is specifically designed for complex object boundaries. Comprehensive experiments support our approach, and our network achieves state of the art performance.
Code (3)
Tasks
Deep LearningInteractive SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Leveraging AI Predicted and Expert Revised Annotations in Interactive Segmentation: Continual Tuning or Full Training?
Interactive segmentation, an integration of AI algorithms and human expertise, premises to improve the accuracy and efficiency of curating large-scale, detailed-annotated datasets in healthcare. Human experts revise the …
Interactive SegmentationA dynamic interactive learning framework for automated 3D medical image segmentation
Many deep learning based automated medical image segmentation systems, in reality, face difficulties in deployment due to the cost of massive data annotation and high latency in model iteration. We propose a dynamic inte…
Image RegistrationImage SegmentationInteractive SegmentationKnowledge Distillation+3Interactive segmentation using U-Net with weight map and dynamic user interactions
Interactive segmentation has recently attracted attention for specialized tasks where expert input is required to further enhance the segmentation performance. In this work, we propose a novel interactive segmentation fr…
Interactive SegmentationSegmentationDeep learning-based interactive segmentation in remote sensing
Interactive segmentation, a computer vision technique where a user provides guidance to help an algorithm segment a feature of interest in an image, has achieved outstanding accuracy and efficient human-computer interact…
Deep LearningInteractive SegmentationLand Cover ClassificationSegmentation+1Interactive4D: Interactive 4D LiDAR Segmentation
Interactive segmentation has an important role in facilitating the annotation process of future LiDAR datasets. Existing approaches sequentially segment individual objects at each LiDAR scan, repeating the process throug…
Interactive SegmentationSegmentation