Depthwise Separable Convolution

Latest papers

9 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Parameter-Efficient 3D Segmentation of Liver and Liver tumors: Depthwise factorization Scales Better Than Dense Convolution with Spatial Dimensionality
Sep 27, 2026Adham M. Alkhadrawi, Mohammed A. B. MahmoudDepthwise Separable Convolution Medical Image Segmentation
Department of Molecular Biosciences and Bioengineering, University of Hawaii at Manoa, Honolulu, HI, USA · Faculty of Computer Studies, Arab Open University, Riyadh 11681, Kingdom of Saudi Arabia
Preprocessing Failure and Adversarial Detection in Depthwise-Separable Edge Vision Systems
Sep 3, 2026Jannatul Masruk Mukta, Rifa Sanjida, Adrita Rahman Tory +2Edge Inference Adversarial Robustness
Bangladesh University of Business and Technology (BUBT), Mirpur-2, Dhaka-1216, Bangladesh · University of New South Wales (UNSW), ACT 2601, Australia
Convolution for Large Language Models
Jul 20, 2026Yuchuan Tian, Yingte Shu, Wei He +7Decoder-Only Language Models Convolutional Neural Networks
1Peking University · 2Huawei Technologies · 3Tsinghua University
SED:Lightweight Saliency prediction for Event-based data via Distillation
Jun 12, 2026Romaric Mazna, Jean Martinet, Michele MagnoEvent-Based Vision Edge Inference
i3S/CNRS, Universit´e Cˆote d’Azur · ETH Zürich
Accelerating Vision Foundation Models with Drop-in Depthwise Convolution
May 21, 2026Carmelo Scribano, Mohammad Mahdi, Nedyalko Prisadnikov +5Vision Foundation Models Vision Foundation Model Adaptation
University of Modena and Reggio Emilia, Modena, Italy. · INSAIT, Sofia University “St. Kliment Ohridski”, Sofia, Bulgaria
Selective Depthwise Separable Convolution for Lightweight Joint Source-Channel Coding in Wireless Image Transmission
Apr 24, 2026Ming Ye, Kui Cai, Cunhua Pan +3Deep Joint Source-Channel Coding Wireless Communications
Singapore University of Technology and Design, Singapore 487372 · National Mobile Communications Research Laboratory, Southeast University, Nanjing 210096, China · School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China
Lightweight Low-Light Image Enhancement via Distribution-Normalizing Preprocessing and Depthwise U-Net
Apr 13, 2026Shimon Murai, Teppei Kurita, Ryuta Satoh +1Depthwise Separable Convolution Low-Light Image Enhancement
Sony Semiconductor Solutions Corporation
ULW-SleepNet: An Ultra-Lightweight Network for Multimodal Sleep Stage Scoring
Feb 27, 2026Zhaowen Wang, Dongdong Zhou, Qi Xu +3Depthwise Separable Convolution Sleep Stage Classification
School of Computer Science and Technology, Dalian University of Technology, Dalian, China · Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland · Key Laboratory of Social Computing and Cognitive Intelligence, Ministry of Education, Dalian, China +3
CLAP Convolutional Lightweight Autoencoder for Plant Disease Classification
Feb 21, 2026Asish Bera, Subhajit Roy, Sudiptendu BanerjeeDepthwise Separable Convolution Plant Disease Classification
Department of Computer Science and Information Systems, Birla Institute of Technology and Science Pilani, Rajasthan, India

Sep 27, 2026J/K move · Enter open · S save

Parameter-Efficient 3D Segmentation of Liver and Liver tumors: Depthwise factorization Scales Better Than Dense Convolution with Spatial Dimensionality

Adham M. Alkhadrawi, Mohammed A. B. Mahmoud

Department of Molecular Biosciences and Bioengineering, University of Hawaii at Manoa, Honolulu, HI, USA · Faculty of Computer Studies, Arab Open University, Riyadh 11681, Kingdom of Saudi Arabia

Depthwise Separable Convolution Medical Image Segmentation 3D Medical Image Segmentation Convolutional Neural Networks U-Net

Open paper AskPDF arXiv

Three-dimensional dense convolutional networks are the strongest performers on volumetric medical image segmentation, but their parameter counts scale poorly: moving a dense k x k convolution to k x k x k multiplies its weights by k. We observe that depthwise separable factorization does not share this penalty. Because the cubic kernel term applies only to the depthwise stage while the pointwise projection, which dominates the parameter count, is unchanged, the same architecture grows by 5 % from 2D to 3D where a dense convolutional U-Net grows by 200 %. We exploit this asymmetry to build a 3D U-Net with 536,990 parameters, 24x fewer than an identical dense 3D U-Net. On MSD Task03 Liver (the Medical Segmentation Decathlon liver task, derived from LiTS), evaluated per case under five-fold cross-validation over all 131 public volumes, the model reaches a tumor Dice of 0.577 (95% CI [0.518, 0.633]) and a liver Dice of 0.947 (95% CI [0.941, 0.952]). Its liver Dice exceeds previously reported performance. Its tumor Dice exceeds their low-resolution configuration (0.4701) by 0.107 and their 2D configuration (0.5394), at approximately one twenty-fourth of the parameters and roughly half the in-plane resolution. Trained under identical conditions on a common held-out split, it exceeds a dense 3D U-Net on liver by +0.031 Dice (paired p = 0.006) and on tumor by +0.041 (95 % CI [+0.005, +0.081], paired p = 0.056), suggesting the factorization also acts as a regularizer in the small-data regime characteristic of medical imaging. We further show, on both LiTS and a 2D endoscopy benchmark, that a large fraction of the network's learnable spatial filters can be replaced by fixed shifts at no cost in accuracy, but that replacing all of them is measurably worse, the placement of spatial capacity matters more than its total amount.