paper-with-me

Papers

Deformable Convolutional Networks

2017-03-17 · ICCV 2017 10 · Jifeng Dai, Haozhi Qi, Yuwen Xiong, Yi Li, Guodong Zhang, Han Hu, Yichen Wei

Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules. In this work, we introduce two new modules to enhance the transformation modeling capacity 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 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 effectiveness of our approach on sophisticated vision tasks of object detection and semantic segmentation. The code would be released.

📄 PDF Abstract BibTeX arXiv:1703.06211

Code (38)

msracver/Deformable-ConvNets 공식 구현 mxnet
DHZS/tf-deformable-conv-layer tf
MonsterPeng/Deformable-ConvNets-master tf
Mukosame/Zooming-Slow-Mo-CVPR-2020 pytorch
NVIDIAAICITYCHALLENGE/AICity_Team6_ISU tf
TangDL/DCN tf
bkvie/Locally-Consistent-Deformable-Convolution pytorch
chenbys/GuidedOffset tf
esw0116/DynaVSR pytorch
fourmi1995/IronExperiment-DCN mxnet
guanfuchen/Deformable-ConvNets tf
hangg7/deformable-kernels pytorch
hangg7/deformable-kernels/ pytorch
liyemei/Deformable-active-convolutional
makefile/frcnn
metaphorz/deep-image-prior-hqskipnet pytorch
necla-ml/Deformable-ConvNets-py3 mxnet
oeway/pytorch-deform-conv pytorch
open-mmlab/mmdetection pytorch
open-mmlab/mmsr pytorch
pytorch/vision pytorch
qilei123/DEEPLAB_4_RETINA tf
qilei123/DEEPLAB_4_RETINAIMG tf
qilei123/DeformableConvV2 mxnet
qilei123/DeformableConvV2_crop mxnet
qilei123/fpn_crop mxnet
qilei123/fpn_crop_v1_5d mxnet
qilei123/sod_v1 mxnet
qilei123/sod_v1_demo mxnet
stupidZZ/pyc_repo mxnet
tianhai123/deform-conv tf
xiaoyongzhu/Deformable-ConvNets mxnet
ximilar-com/xcenternet tf
xinntao/EDVR pytorch
zengzhaoyang/Weak_Detection tf
zengzhaoyang/trident mxnet
zhusiling/EDVR pytorch
zzdxfei/defor_conv_mxnet_code mxnet

Tasks

Object DetectionSemantic SegmentationVessel Detection

Methods 이 논문이 사용한 방법론

Deformable ConvNets Deformable ConvNets do not learn an affine transformation. They divide convolution into two steps, firstly sampling features on a regular grid $ \mathcal{R} $ from the input…
Average Pooling 설명 없음
Residual Connection 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Similar Papers 제목 키워드 기반

Deep Deformable Registration: Enhancing Accuracy by Fully Convolutional Neural Net

2016-11-27 · Sayan Ghosal, Nilanjan Ray

Deformable registration is ubiquitous in medical image analysis. Many deformable registration methods minimize sum of squared difference (SSD) as the registration cost with respect to deformable model parameters. In this…

Medical Image Analysis

An Efficient Accelerator Design Methodology for Deformable Convolutional Networks

2020-06-09 · Saehyun Ahn, Jung-Woo Chang, Suk-Ju Kang

Deformable convolutional networks have demonstrated outstanding performance in object recognition tasks with an effective feature extraction. Unlike standard convolution, the deformable convolution decides the receptive …

Object Recognition

LDConv: Linear deformable convolution for improving convolutional neural networks

2023-11-20 · Xin Zhang, Yingze Song, Tingting Song, Degang Yang 외

Neural networks based on convolutional operations have achieved remarkable results in the field of deep learning, but there are two inherent flaws in standard convolutional operations. On the one hand, the convolution op…

object-detectionObject Detection

ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding

2018-11-29 · CVPR 2019 6 · Ning Liu, Yongchao Long, Changqing Zou, Qun Niu 외

We propose an attention-injective deformable convolutional network called ADCrowdNet for crowd understanding that can address the accuracy degradation problem of highly congested noisy scenes. ADCrowdNet contains two con…

Crowd Counting

3D Deformable Convolutions for MRI classification

2019-11-05 · Marina Pominova, Ekaterina Kondrateva, Maksim Sharaev, Sergey Pavlov 외

Deep learning convolutional neural networks have proved to be a powerful tool for MRI analysis. In current work, we explore the potential of the deformable convolutional deep neural network layers for MRI data classifica…

ClassificationGeneral ClassificationMRI classification