Search Results - Depthwise convolution

Fusing Depthwise and Pointwise Convolutions for Efficient Inference on GPUs

Authors: Mohammad Qararyah, Fareed Azhar, Muhammad Waqar Maleki, Mohammad Ali et al.

Source: Very Efficient Deep Learning in IOT (VEDLIoT) EPI SGA2 53rd International Conference on Parallel Processing, ICPP 2024, Gotland, Sweden ACM International Conference Proceeding Series. :58-67

Subject Terms: layer fusion, depthwise convolution, CNN, vision transformer, pointwise convolution, GPU

File Description: electronic

Access URL: https://research.chalmers.se/publication/542723
https://research.chalmers.se/publication/543131
https://research.chalmers.se/publication/543131/file/543131_Fulltext.pdf

Area-Specific Convolutional Neural Network with Depthwise Convolution for Super-Resolution

Authors: Seeun Kim Hyunji Lee Kyujoong Lee

Source: Journal of Korea Multimedia Society. 28:733-740

Lightweight Self-Supervised Monocular Depth Estimation via Context-Aware Fusion and Separable Depthwise Convolution

Authors: Meina Zhao Shixin Wang Feng Xiao et al.

Source: 2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD). :1289-1294

Depthwise Convolution with Winograd Algorithm for Efficient CNN Acceleration

Authors: Ping-Jung Chung Chi-Tang Chen Wei-Cheng Chueh et al.

Source: 2025 IEEE Gaming, Entertainment, and Media Conference (GEM). :1-3

Lightweight pavement defect detection algorithm combining Partial Convolution and Inception Depthwise Convolution

Authors: Yi Peng Yufei Shao

Source: Journal of Image and Graphics. 0:1-19

LightFormer: Vision Transformer for Lightweight Based on Cascade Depthwise Convolution and Mixed Attention

Authors: Falin Wang Jian Ji Yuan Wang et al.

Source: IEEE Transactions on Geoscience and Remote Sensing. 63:1-12

SEFormer: A Lightweight CNN-Transformer Based on Separable Multiscale Depthwise Convolution and Efficient Self-Attention for Rotating Machinery Fault Diagnosis

Authors: Hongxing Wang Hua Zhu Huafeng Li et al.

Source: Computers, Materials & Continua. 82:1417-1437

DSConvNet: A Lightweight Architecture for Extracting Image Features From Depthwise Separable Convolution Network for Edge Devices

Authors: Syed Muhammad Raza Syed Murtaza Hussain Abidi Md Masuduzzaman et al.

Source: IEEE Access, Vol 13, Pp 210102-210116 (2025)

Subject Terms: Depthwise separable convolution network, image feature extraction, image classification, lightweight architecture, model compression, resource-constrained devices, Electrical engineering. Electronics. Nuclear engineering, TK1-9971

File Description: electronic resource

Relation: https://ieeexplore.ieee.org/document/11272073/; https://doaj.org/toc/2169-3536

Access URL: https://doaj.org/article/88f6b09790d34f33a329a03359941e0c

Optimizing depthwise separable convolution on DCU

Authors: Zheng Liu Meng Hao Weizhe Zhang et al.

Source: CCF Transactions on High Performance Computing. 6:646-664

Subject Terms: 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology, 01 natural sciences

BiRD: Bi-Directional Input Reuse Dataflow for Enhancing Depthwise Convolution Performance on Systolic Arrays

Authors: Mingeon Park Seokjin Hwang Hyungmin Cho

Source: IEEE Transactions on Computers. 73:2708-2721

Enhanced YOLOv8 Model for Insulator Defect Detection using Generalized Loss and Depthwise Convolution Techniques

Authors: Song Yang Ming Liu Xinqiang Wu et al.

Source: 2024 5th International Conference on Artificial Intelligence and Computer Engineering (ICAICE). :1093-1097

Research on Image Classification Method Based on Depthwise Convolution Combined with Improved Transformer Model

Authors: Wei Lin

Source: 2024 8th Asian Conference on Artificial Intelligence Technology (ACAIT). :1488-1493

EDEA: Efficient Dual-Engine Accelerator for Depthwise Separable Convolution with Direct Data Transfer

Authors: Chen, Yi Lou, Jie Wabnitz, Malte et al.

Source: 2024 IEEE 37th International System-on-Chip Conference (SOCC). :1-6

Subject Terms: FOS: Computer and information sciences, Computer Science - Distributed, Parallel, and Cluster Computing, Hardware Architecture (cs.AR), Distributed, Parallel, and Cluster Computing (cs.DC), Computer Science - Hardware Architecture

Access URL: http://arxiv.org/abs/2503.11707

A Hybrid Model Combining Depthwise Separable Convolutions and Vision Transformers for Traffic Sign Classification Under Challenging Weather Conditions

Authors: Milind Vijay Parse Dhanya Pramod Deepak Kumar

Source: International Journal of System Assurance Engineering and Management. 16:2720-2742

Design of spatial channel attention mechanism based on depthwise convolution

Authors: Suk-Hyang Ri Kwang-Chol Ri

Source: Multimedia Tools and Applications.

Depthwise Convolution for Multi-Agent Communication With Enhanced Mean-Field Approximation

Authors: Donghan Xie Zhi Wang Chunlin Chen et al.

Source: IEEE Transactions on Neural Networks and Learning Systems. 35:8557-8569

Subject Terms: FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, 0202 electrical engineering, electronic engineering, information engineering, Computer Science - Multiagent Systems, 02 engineering and technology, 01 natural sciences, Machine Learning (cs.LG), Multiagent Systems (cs.MA), 0105 earth and related environmental sciences

Access URL: https://pubmed.ncbi.nlm.nih.gov/37015645
http://arxiv.org/abs/2203.02896

KIDBA‐Net: A Multi‐Feature Fusion Brain Tumor Segmentation Network Utilizing Kernel Inception Depthwise Convolution and Bi‐Cross Attention

Authors: Jie Min Tongyuan Huang Boxiong Huang et al.

Source: International Journal of Imaging Systems and Technology. 35

VarKFaceNet: An Efficient Variable Depthwise Convolution Kernels Neural Network for Lightweight Face Recognition

Authors: Qinghua Ma Peng Zhang Min Cui

Source: IEEE Access, Vol 12, Pp 117472-117482 (2024)

Subject Terms: 03 medical and health sciences, 0302 clinical medicine, multi-scale, lightweight network, 0202 electrical engineering, electronic engineering, information engineering, Electrical engineering. Electronics. Nuclear engineering, 02 engineering and technology, Face recognition, local features, TK1-9971

Access URL: https://doaj.org/article/e9e48c64a0c8406780c69656f747ce7c

Multiscale Residual Network with Dynamic Depthwise Convolution for Multi-label 12-Lead ECG Classification

Authors: Linhai Xie Yilei Man Delong Shang

Source: 2024 International Joint Conference on Neural Networks (IJCNN). :1-8

A Swin transformer enhanced Depthwise convolution with dynamic channel reweighting for partial discharge diagnosis in gas insulated switchgear

Authors: Yanqi Liu Wendong Li Xiaochang Hua et al.

Source: Electric Power Systems Research. 248:111993