Lightweight Convolutional Neural Network

Lightweight convolutional neural networks (CNNs) aim to achieve high performance in image-related tasks while minimizing computational resources and memory footprint, making them suitable for deployment on resource-constrained devices like mobile phones and embedded systems. Current research focuses on developing novel architectures, such as those incorporating attention mechanisms, multi-scale feature representations, and structural reparameterization, to improve efficiency without sacrificing accuracy. These advancements are significant for various applications, including real-time object detection, medical image analysis, and mobile vision tasks, enabling broader accessibility and deployment of powerful CNN models.

Papers

November 1, 2024

A lightweight Convolutional Neural Network based on U shape structure and Attention Mechanism for Anterior Mediastinum Segmentation
Sina Soleimani-Fard, Won Gi Jeong, Francis Ferri Ripalda, Hasti Sasani, Younhee Choi, S Deiva, Gong Yong Jin, Seok-bum Ko
Attention Mechanism Segmentation Performance Automatic Segmentation U Shaped Network Lightweight Convolutional Neural Network U Shaped Mediastinal Lymph Node

September 19, 2024

Enhancing Construction Site Safety: A Lightweight Convolutional Network for Effective Helmet Detection
Mujadded Al Rabbani Alif
Convolutional Neural Network Convolutional Block Lightweight Convolutional Neural Network Construction Progress Monitoring

June 23, 2024

RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization
Mingshu Zhao, Yi Luo, Yong Ouyang
Convolutional Neural Network Vision Transformer Multi Scale Vision Model Lightweight Convolutional Neural Network

April 1, 2024

BloodCell-Net: A lightweight convolutional neural network for the classification of all microscopic blood cell images of the human body
Sohag Kumar Mondal, Md. Simul Hasan Talukder, Mohammad Aljaidi, Rejwan Bin Sulaiman, Md Mohiuddin Sarker Tushar, Amjad A Alsuwaylimi
Classification Code Human Body Lightweight Convolutional Neural Network Watershed Algorithm Blood Smear Blood Cell Image

February 28, 2024

Generalizable Two-Branch Framework for Image Class-Incremental Learning
Chao Wu, Xiaobin Chang, Ruixuan Wang
Deep Neural Network Catastrophic Forgetting Continual Learning Class Incremental Learning Dual Branch Lightweight Convolutional Neural Network

January 31, 2024

Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model
Zihan Zhong, Zhiqiang Tang, Tong He, Haoyang Fang, Chun Yuan
Semantic Segmentation Segment Anything Model Direct Convolution Low Rank Adaptation Parameter Efficient Foreground Object Lightweight Convolutional Neural Network

November 7, 2023

A Comparative Study of Knowledge Transfer Methods for Misaligned Urban Building Labels
Bipul Neupane, Jagannath Aryal, Abbas Rajabifard
Neural Network Semantic Segmentation Computer Vision Comparative Study Knowledge Transfer Lightweight Convolutional Neural Network Building Footprint Positional Label

October 13, 2023

Efficient Apple Maturity and Damage Assessment: A Lightweight Detection Model with GAN and Attention Mechanism
Yufei Liu, Manzhou Li, Qin Ma
Generative Adversarial Network GAN Model Attention Mechanism Damage Detection Lightweight Convolutional Neural Network Apple Detection Maturity Level Lightweight Detection

August 17, 2023

MovePose: A High-performance Human Pose Estimation Algorithm on Mobile and Edge Devices
Dongyang Yu, Haoyue Zhang, Ruisheng Zhao, Guoqi Chen, Wangpeng An, Yanhong Yang
Real Time Edge Device Human Pose Estimation Mobile User Lightweight Convolutional Neural Network Posture Estimation

August 14, 2023

iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN
Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Shogo Seki
Convolutional Neural Network Speech Synthesis Neural Vocoder Short Time Fourier Transform Upsampling Module Lightweight Convolutional Neural Network

July 20, 2023

Reverse Knowledge Distillation: Training a Large Model using a Small One for Retinal Image Matching on Limited Data
Sahar Almahfouz Nasser, Nihar Gupte, Amit Sethi
Vision Transformer Knowledge Distillation Large Model Image Analysis Limited Data Keypoint Detection Retinal Image Lightweight Convolutional Neural Network

July 18, 2023

RepViT: Revisiting Mobile CNN From ViT Perspective
Ao Wang, Hui Chen, Zijia Lin, Jungong Han, Guiguang Ding
Convolutional Neural Network Lightweight Convolutional Neural Network Lightweight CNN Mobile CNN Lightweight Vision Transformer

January 27, 2023

A Memory Efficient Deep Reinforcement Learning Approach For Snake Game Autonomous Agents
Md. Rafat Rahman Tushar, Shahnewaz Siddique
Reinforcement Learning Deep Reinforcement Learning Memory Replay Snake Robot Lightweight Convolutional Neural Network Conservative Reward

December 15, 2022

Colab NAS: Obtaining lightweight task-specific convolutional neural networks following Occam's razor
Andrea Mattia Garavagno, Daniele Leonardis, Antonio Frisoli
Convolutional Neural Network Lightweight Convolutional Neural Network Hardware Aware Neural Architecture Search Occam Algorithm Google AI Light Weight

September 16, 2022

LO-Det: Lightweight Oriented Object Detection in Remote Sensing Images
Zhanchao Huang, Wei Li, Xiang-Gen Xia, Hao Wang, Feiran Jie, Ran Tao
Object Detector Remote Sensing Image Convolution Kernel Separable Convolution Lightweight Convolutional Neural Network Remote Sensing Object Detection Lightweight Object Detection

September 14, 2022

July 20, 2022

Locality Guidance for Improving Vision Transformers on Tiny Datasets
Kehan Li, Runyi Yu, Zhennan Wang, Li Yuan, Guoli Song, Jie Chen
Convolutional Neural Network Vision Transformer Lightweight Convolutional Neural Network Small Scale Datasets

June 26, 2022

CTMQ: Cyclic Training of Convolutional Neural Networks with Multiple Quantization Steps
HyunJin Kim, Jungwoo Shin, Alberto A. Del Barrio
Convolutional Neural Network Lightweight Convolutional Neural Network Quantization Step Bit Depth Cyclic Training

April 2, 2022

Efficient Convolutional Neural Networks on Raspberry Pi for Image Classification
Rui-Yang Ju, Ting-Yu Lin, Jia-Hao Jian, Jen-Shiun Chiang
Convolutional Neural Network Image Classification L MobileNet Lightweight Convolutional Neural Network Raspberry Pi

Lightweight Convolutional Neural Network

Papers

A lightweight Convolutional Neural Network based on U shape structure and Attention Mechanism for Anterior Mediastinum Segmentation

Enhancing Construction Site Safety: A Lightweight Convolutional Network for Effective Helmet Detection

RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization

BloodCell-Net: A lightweight convolutional neural network for the classification of all microscopic blood cell images of the human body

Generalizable Two-Branch Framework for Image Class-Incremental Learning

Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model

A Comparative Study of Knowledge Transfer Methods for Misaligned Urban Building Labels

Efficient Apple Maturity and Damage Assessment: A Lightweight Detection Model with GAN and Attention Mechanism

MovePose: A High-performance Human Pose Estimation Algorithm on Mobile and Edge Devices

iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN

Reverse Knowledge Distillation: Training a Large Model using a Small One for Retinal Image Matching on Limited Data

RepViT: Revisiting Mobile CNN From ViT Perspective

A Memory Efficient Deep Reinforcement Learning Approach For Snake Game Autonomous Agents

Colab NAS: Obtaining lightweight task-specific convolutional neural networks following Occam's razor

LO-Det: Lightweight Oriented Object Detection in Remote Sensing Images

NanoFlowNet: Real-time Dense Optical Flow on a Nano Quadcopter

FCDSN-DC: An Accurate and Lightweight Convolutional Neural Network for Stereo Estimation with Depth Completion

Locality Guidance for Improving Vision Transformers on Tiny Datasets

CTMQ: Cyclic Training of Convolutional Neural Networks with Multiple Quantization Steps

Efficient Convolutional Neural Networks on Raspberry Pi for Image Classification