Path Aggregation Network for Instance Segmentation

Abstract

The way that information propagates in neural networks is of great importance. In this paper, we propose Path Aggregation Network (PANet) aiming at boosting information flow in proposal-based instance segmentation framework. Specifically, we enhance the entire feature hierarchy with accurate localization signals in lower layers by bottom-up path augmentation, which shortens the information path between lower layers and topmost feature. We present adaptive feature pooling, which links feature grid and all feature levels to make useful information in each level propagate directly to following proposal subnetworks. A complementary branch capturing different views for each proposal is created to further improve mask prediction. These improvements are simple to implement, with subtle extra computational overhead. Yet they are useful and make our PANet reach the 1st place in the COCO 2017 Challenge Instance Segmentation task and the 2nd place in Object Detection task without large-batch training. PANet is also state-of-the-art on MVD and Cityscapes. © 2018 IEEE.

Keywords

Computer sciencePoolingSegmentationFeature (linguistics)Artificial intelligencePath (computing)Boosting (machine learning)GridTask (project management)Overhead (engineering)Pyramid (geometry)Pattern recognition (psychology)Machine learningData miningEngineering

Affiliated Institutions

Related Publications

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

Coordinate Attention for Efficient Mobile Network Design

Qibin Hou , Daquan Zhou , Jiashi Feng

Recent studies on mobile network design have demonstrated the remarkable effectiveness of channel attention (e.g., the Squeeze-and-Excitation attention) for lifting model perfor...

2021 2021 IEEE/CVF Conference on Computer ... 4986 citations

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

Fractional Max-Pooling

Benjamin Graham

Convolutional networks almost always incorporate some form of spatial pooling, and very often it is alpha times alpha max-pooling with alpha=2. Max-pooling act on the hidden lay...

2014 arXiv (Cornell University) 335 citations

Network In Network

Min Lin , Qiang Chen , Shuicheng Yan

Abstract: We propose a novel deep network structure called In Network (NIN) to enhance model discriminability for local patches within the receptive field. The conventional con...

2014 arXiv (Cornell University) 1037 citations

Publication Info

Year: 2018
Type: preprint
Pages: 8759-8768
Citations: 7956
Access: Closed

External Links

Download PDF (Free) View on DOI.org arXiv Semantic Scholar

Social Impact

Altmetric

Path Aggregation Network for Instance Segmentation

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

7956

OpenAlex

536

Influential

6838

CrossRef

Cite This

APA Style

                            
                                    Shu Liu, 
                                
                                    Lu Qi, 
                                
                                    Haifang Qin
                                
                                et al.
                            
                            (2018). 
                            Path Aggregation Network for Instance Segmentation. 
                            2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
                            
                            , 8759-8768.
                            https://doi.org/10.1109/cvpr.2018.00913

Identifiers

DOI: 10.1109/cvpr.2018.00913
arXiv: 1803.01534

Data Quality

Data completeness: 84%