Deformable Convolutional Networks | RDL Research Database

Abstract

Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in their building modules. In this work, we introduce two new modules to enhance the transformation modeling capability of CNNs, namely, deformable convolution and deformable RoI pooling. Both are based on the idea of augmenting the spatial sampling locations in the modules with additional offsets and learning the offsets from the target tasks, without additional supervision. The new modules can readily replace their plain counterparts in existing CNNs and can be easily trained end-to-end by standard back-propagation, giving rise to deformable convolutional networks. Extensive experiments validate the performance of our approach. For the first time, we show that learning dense spatial transformation in deep CNNs is effective for sophisticated vision tasks such as object detection and semantic segmentation. The code is released at https://github.com/msracver/Deformable-ConvNets.

Keywords

Computer sciencePoolingArtificial intelligenceConvolutional neural networkConvolution (computer science)Transformation (genetics)SegmentationCode (set theory)Deep learningComputer visionPattern recognition (psychology)Object detectionGeometric transformationArtificial neural networkImage (mathematics)

Affiliated Institutions

Microsoft Research Asia (China) CN

Related Publications

Deformable ConvNets V2: More Deformable, Better Results

Xizhou Zhu , Han Hu , Stephen Lin +1 more

The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects. Through an examination of its adaptive beh...

2019 2019 IEEE/CVF Conference on Computer ... 2431 citations

Swin-Unet: Unet-Like Pure Transformer for Medical Image Segmentation

Hu Cao , Yueyue Wang , Joy Chen +4 more

In the past few years, convolutional neural networks (CNNs) have achieved milestones in medical image analysis. Especially, the deep neural networks based on U-shaped architectu...

2023 Lecture notes in computer science 2757 citations

RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation

Guosheng Lin , Anton Milan , Chunhua Shen +1 more

Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification pr...

2017 3120 citations

DeepID-Net: Deformable deep convolutional neural networks for object detection

Wanli Ouyang , Xiaogang Wang , Xingyu Zeng +8 more

In this paper, we propose deformable deep convolutional neural networks for generic object detection.This new deep learning object detection framework has innovations in multipl...

2015 429 citations

Global Second-Order Pooling Convolutional Networks

Zilin Gao , Jiangtao Xie , Qilong Wang +1 more

Deep Convolutional Networks (ConvNets) are fundamental to, besides large-scale visual recognition, a lot of vision tasks. As the primary goal of the ConvNets is to characterize ...

2019 461 citations

Publication Info

Year: 2017
Type: article
Pages: 764-773
Citations: 6444
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Deformable Convolutional Networks

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

6444

OpenAlex

Cite This

APA Style

                            
                                    Jifeng Dai, 
                                
                                    Haozhi Qi, 
                                
                                    Yuwen Xiong
                                
                                et al.
                            
                            (2017). 
                            Deformable Convolutional Networks. 
                            
                            , 764-773.
                            https://doi.org/10.1109/iccv.2017.89

Identifiers

DOI: 10.1109/iccv.2017.89