Fully Convolutional Instance-aware Semantic Segmentation
arXiv:1611.07709
Abstract
We present the first fully convolutional end-to-end solution for instance-aware semantic segmentation task. It inherits all the merits of FCNs for semantic segmentation and instance mask proposal. It performs instance mask prediction and classification jointly. The underlying convolutional representation is fully shared between the two sub-tasks, as well as between all regions of interest. The proposed network is highly integrated and achieves state-of-the-art performance in both accuracy and efficiency. It wins the COCO 2016 segmentation competition by a large margin. Code would be released at \url{https://github.com/daijifeng001/TA-FCN}.
Cited by in corpus (23)
- Semantic Instance Segmentation via Deep Metric Learning
- Rain Removal in Traffic Surveillance: Does it Matter?
- Relation Networks for Object Detection
- Multiple-Human Parsing in the Wild
- PixelLink: Detecting Scene Text via Instance Segmentation
- Fully Convolutional Networks for Chip-wise Defect Detection Employing Photoluminescence Images
- IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection
- Camera-based vehicle velocity estimation from monocular video
- Scene Text Detection with Supervised Pyramid Context Network
- Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery
- ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving
- Learning Deep Representations for Semantic Image Parsing: a Comprehensive Overview
- Beef Cattle Instance Segmentation Using Fully Convolutional Neural Network
- Semantically-Guided Video Object Segmentation
- Instance Segmentation of Visible and Occluded Regions for Finding and Picking Target from a Pile of Objects
- PointIT: A Fast Tracking Framework Based on 3D Instance Segmentation
- Picasso: A Modular Framework for Visualizing the Learning Process of Neural Network Image Classifiers
- DeepSkeleton: Skeleton Map for 3D Human Pose Regression
- Deep Variational Instance Segmentation
- Semantic and structural image segmentation for prosthetic vision
- Dynamic Filtering with Large Sampling Field for ConvNets
- Selective Information Passing for MR/CT Image Segmentation
- Organ At Risk Segmentation with Multiple Modality