.png){kind=icon}
Return
HDConv: Heterogeneous kernel-based dilated convolutions
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2024.106568.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Dilated convolution has been widely used in various computer vision tasks due to its ability to expand the receptive field while maintaining the resolution of feature maps. However, the critical challenge is the gridding problem caused by the isomorphic structure of the dilated convolution, where the holes filled in the dilated convolution destroy the integrity of the extracted information and cut off the relevance of neighboring pixels. In this work, a novel heterogeneous dilated convolution, called HDConv, is proposed to address this issue by setting independent dilation rates on grouped channels while keeping the general convolution operation. The heterogeneous structure can effectively avoid the gridding problem while introducing multi-scale kernels in the filters. Based on the heterogeneous structure of the proposed HDConv, we also explore the benefit of large receptive fields to feature extraction by comparing different combinations of dilated rates. Finally, a series of experiments are conducted to verify the effectiveness of some computer vision tasks, such as image segmentation and object detection. The results show the proposed HDConv can achieve a competitive performance on ADE20K, Cityscapes, COCO-Stuff10k, COCO, and a medical image dataset UESTC-COVID-19. The proposed module can readily replace conventional convolutions in existing convolutional neural networks (i.e., plug-and-play), and it is promising to further extend dilated convolution to wider scenarios in the field of image segmentation.
Keywords:
Dilated convolution
Image segmentation
Receptive field
Heterogeneous structure
Journal
IF:
6.3
Papers:
8.2K
Citations:
3.0W
Organization
Cited Papers
Deep co-supervision and attention fusion strategy for automatic COVID-19 lung infection segmentation on CT images.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAIShareSaveIn vitro and in vivo binding of neuroactive steroids to the sigma‐1 receptor as measured with the positron emission tomography radioligand [18F]FPSSynapse
SynapseIF0
PREAI
ShareSaveRecent Development of Dual-Dictionary Learning Approach in Medical Image Analysis and ReconstructionOAAI
OAAIShareSaveCandidate .gamma.-Secretases in the Generation of the Carboxyl Terminus of the Alzheimer's Disease .beta.A4 Amyloid: Possible Involvement of Cathepsin DBiochemistry
BiochemistryIF0
PREAI
ShareSaveSynthesis of n-type semiconducting diamond film using diphosphorus pentaoxide as the doping source
PREAI
ShareSaveEnergy-Efficient Robot Configuration and Motion Planning Using Genetic Algorithm and Particle Swarm OptimizationEnergies
OAAI
EnergiesIF0
OAAIShareSave
View more