Mask R-CNN

Abstract

We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. Mask R-CNN is simple to train and adds only a small overhead to Faster R-CNN, running at 5 fps. Moreover, Mask R-CNN is easy to generalize to other tasks, e.g., allowing us to estimate human poses in the same framework. We show top results in all three tracks of the COCO suite of challenges, including instance segmentation, bounding-box object detection, and person keypoint detection. Without bells and whistles, Mask R-CNN outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners. We hope our simple and effective approach will serve as a solid baseline and help ease future research in instance-level recognition. Code has been made available at: https://github.com/facebookresearch/Detectron

open source; appendix on more results

Cited by in corpus (29)

• Automatic Colon Polyp Detection using Region based Deep CNN and Post Learning Approaches
• RGB-D Object Detection and Semantic Segmentation for Autonomous Manipulation in Clutter
• Vehicle Tracking Using Surveillance with Multimodal Data Fusion
• Image-Based Size Analysis of Agglomerated and Partially Sintered Particles via Convolutional Neural Networks
• Deep learning for clustering of continuous gravitational wave candidates
• Port-Hamiltonian Neural Networks for Learning Explicit Time-Dependent Dynamical Systems
• Lesion Segmentation in Ultrasound Using Semi-pixel-wise Cycle Generative Adversarial Nets
• Global-Reasoned Multi-Task Learning Model for Surgical Scene Understanding
• Automated Defect Recognition of Castings defects using Neural Networks
• Panoptic Instance Segmentation on Pigs
• Improving the Detection of Small Oriented Objects in Aerial Images
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Efficient Deep Learning Models for Privacy-preserving People Counting on Low-resolution Infrared Arrays
• Automated Quality Control of Vacuum Insulated Glazing by Convolutional Neural Network Image Classification
• Advances in Deep Space Exploration via Simulators & Deep Learning
• EdgeNet: Balancing Accuracy and Performance for Edge-based Convolutional Neural Network Object Detectors
• ExSample: Efficient Searches on Video Repositories through Adaptive Sampling
• HRCenterNet: An Anchorless Approach to Chinese Character Segmentation in Historical Documents
• OMG-Net: A Deep Learning Framework Deploying Segment Anything to Detect Pan-Cancer Mitotic Figures from Haematoxylin and Eosin-Stained Slides
• Edge Devices Inference Performance Comparison
• FOTS: Fast Oriented Text Spotting with a Unified Network
• Virtual Underwater Datasets for Autonomous Inspections
• Picasso: A Modular Framework for Visualizing the Learning Process of Neural Network Image Classifiers
• Vision and Tactile Robotic System to Grasp Litter in Outdoor Environments
• Predicting bulge to total luminosity ratio of galaxies using deep learning
• Eliminating artefacts in Polarimetric Images using Deep Learning
• Deep unsupervised domain adaptation applied to the Cherenkov Telescope Array Large-Sized Telescope
• Investigation of a Machine learning methodology for the SKA pulsar search pipeline
• Deep Learning for Accurate Vision-based Catch Composition in Tropical Tuna Purse Seiners