Deep Interactive Object Selection

Abstract

Interactive object selection is a very important research problem and has many applications. Previous algorithms require substantial user interactions to estimate the foreground and background distributions. In this paper, we present a novel deep learning based algorithm which has a much better understanding of objectness and thus can reduce user interactions to just a few clicks. Our algorithm transforms user provided positive and negative clicks into two Euclidean distance maps which are then concatenated with the RGB channels of images to compose (image, user interactions) pairs. We generate many of such pairs by combining several random sampling strategies to model user click patterns and use them to fine tune deep Fully Convolutional Networks (FCNs). Finally the output probability maps of our FCN 8s model is integrated with graph cut optimization to refine the boundary segments. Our model is trained on the PASCAL segmentation dataset and evaluated on other datasets with different object classes. Experimental results on both seen and unseen objects clearly demonstrate that our algorithm has a good generalization ability and is superior to all existing interactive object selection approaches.

Computer Vision and Pattern Recognition

References in corpus (2)

• Fully Convolutional Networks for Semantic Segmentation
• Semantic Image Segmentation via Deep Parsing Network

Cited by in corpus (18)

• Few-Shot Segmentation Propagation with Guided Networks
• Learning Video Object Segmentation from Static Images
• Interactive segmentation of medical images through fully convolutional neural networks
• CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning
• Interactive Video Object Segmentation in the Wild
• Simple Does It: Weakly Supervised Instance and Semantic Segmentation
• Real-Time User-Guided Image Colorization with Learned Deep Priors
• Iteratively Trained Interactive Segmentation
• CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation
• Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning
• Deep GrabCut for Object Selection
• Deep Extreme Cut: From Extreme Points to Object Segmentation
• ClickBAIT-v2: Training an Object Detector in Real-Time
• DISIR: Deep Image Segmentation with Interactive Refinement
• Pixelwise Instance Segmentation with a Dynamically Instantiated Network
• A-Lamp: Adaptive Layout-Aware Multi-Patch Deep Convolutional Neural Network for Photo Aesthetic Assessment
• Autonomous Curiosity for Real-Time Training Onboard Robotic Agents
• Localized Interactive Instance Segmentation