Fully Convolutional Instance-Aware Semantic Segmentation

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 [29] and instance mask proposal [5]. 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 network architecture is highly integrated and efficient. It 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 https://github.com/daijifeng001/TA-FCN.

Keywords

Computer scienceSegmentationMargin (machine learning)Artificial intelligenceRepresentation (politics)Convolutional neural networkTask (project management)Code (set theory)Convolutional codePattern recognition (psychology)Machine learningAlgorithmDecoding methodsProgramming language

Affiliated Institutions

Related Publications

UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation

Zongwei Zhou , Md Mahfuzur Rahman Siddiquee , Nima Tajbakhsh +1 more

The state-of-the-art models for medical image segmentation are variants of U-Net and fully convolutional networks (FCN). Despite their success, these models have two limitations...

2019 IEEE Transactions on Medical Imaging 3567 citations

Fully convolutional networks for semantic segmentation

Jonathan Long , Evan Shelhamer , Trevor Darrell

Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, ex...

2015 35498 citations

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions

Wenhai Wang , Enze Xie , Xiang Li +6 more

Although convolutional neural networks (CNNs) have achieved great success in computer vision, this work investigates a simpler, convolution-free backbone network use-fid for man...

2021 2021 IEEE/CVF International Conferenc... 4221 citations

Learning Deconvolution Network for Semantic Segmentation

Hyeonwoo Noh , Seunghoon Hong , Bohyung Han

We propose a novel semantic segmentation algorithm by learning a deep deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer ne...

2015 3978 citations

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

Ze Liu , Yutong Lin , Yue Cao +5 more

This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer ...

2021 2021 IEEE/CVF International Conferenc... 25813 citations

Publication Info

Year: 2017
Type: preprint
Citations: 1120
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Fully Convolutional Instance-Aware Semantic Segmentation

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

1120

OpenAlex

Cite This

APA Style

                            
                                    Yi Li, 
                                
                                    Haozhi Qi, 
                                
                                    Jifeng Dai
                                
                                et al.
                            
                            (2017). 
                            Fully Convolutional Instance-Aware Semantic Segmentation. 
                            
                            .
                            https://doi.org/10.1109/cvpr.2017.472

Identifiers

DOI: 10.1109/cvpr.2017.472