Deep Extreme Cut: From Extreme Points to Object Segmentation

2017/11/24 by Kevis-Kokitsi Maninis, Maninis, Kevis-Kokitsi, Sergi Caelles +5 · 10 citations
Computer Science · #Advanced Neural Network Applications #Visual Attention and Saliency Detection #Advanced Image and Video Retrieval Techniques

paper · pdf · doi:10.48550/arxiv.1711.09081

Abstract

This paper explores the use of extreme points in an object (left-most, right-most, top, bottom pixels) as input to obtain precise object segmentation for images and videos. We do so by adding an extra channel to the image in the input of a convolutional neural network (CNN), which contains a Gaussian centered in each of the extreme points. The CNN learns to transform this information into a segmentation of an object that matches those extreme points. We demonstrate the usefulness of this approach for guided segmentation (grabcut-style), interactive segmentation, video object segmentation, and dense segmentation annotation. We show that we obtain the most precise results to date, also with less user input, in an extensive and varied selection of benchmarks and datasets. All our models and code are publicly available on http://www.vision.ee.ethz.ch/~cvlsegmentation/dextr/.

Cited by

• Uncertainty-Aware Extreme Point Tracing for Weakly Supervised Ultrasound Image Segmentation
• Towards Efficient Pixel Labeling for Industrial Anomaly Detection and Localization
• Towards PerSense++: Advancing Training-Free Personalized Instance Segmentation in Dense Images
• Block Annotation: Better Image Annotation for Semantic Segmentation with Sub-Image Decomposition
• Inter2Former: Dynamic Hybrid Attention for Efficient High-Precision Interactive
• PolyTransform: Deep Polygon Transformer for Instance Segmentation
• One-Shot Segmentation in Clutter
• Interactive segmentation of medical images through fully convolutional neural networks
• Interactive Instance Annotation with Siamese Networks
• Weakly Labeling the Antarctic: The Penguin Colony Case

Related

• FAIRS -- Soft Focus Generator and Attention for Robust Object Segmentation from Extreme Points
• DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks
• Pixel-Level Matching for Video Object Segmentation using Convolutional\n Neural Networks
• Deep GrabCut for Object Selection
• Interactive Video Object Segmentation in the Wild