Convolution Operation

The convolution operation, a fundamental building block of convolutional neural networks (CNNs), aims to extract features from data by applying a filter across multiple spatial locations. Current research focuses on improving convolution's efficiency and effectiveness, exploring variations like Winograd convolutions for faster computation, incorporation of involution and transformer architectures for enhanced feature extraction and long-range dependency modeling, and optimizations for reduced-precision arithmetic and hardware acceleration. These advancements are crucial for improving the performance and energy efficiency of CNNs across diverse applications, including medical image analysis, robotic manipulation, and computer vision tasks.

Papers

October 28, 2024

SparseTem: Boosting the Efficiency of CNN-Based Video Encoders by Exploiting Temporal Continuity
Kunyun Wang, Jieru Zhao, Shuo Yang, Wenchao Ding, Minyi Guo
Convolutional Neural Network High Efficiency Convolution Operation Video Processing Video Encoder

September 27, 2024

Med-IC: Fusing a Single Layer Involution with Convolutions for Enhanced Medical Image Classification and Segmentation
Md. Farhadul Islam, Sarah Zabeen, Meem Arafat Manab, Mohammad Rakibul Hasan Mahin, Joyanta Jyoti Mondal, Md. Tanzim Reza, Md Zahidul Hasan, Munima Haque, Farig Sadeque, Jannatun Noor
Convolutional Neural Network Segmentation Based Approach Direct Convolution Medical Image Classification Convolution Operation Reversible Architecture

September 18, 2024

Tight and Efficient Upper Bound on Spectral Norm of Convolutional Layers
Ekaterina Grishina, Mikhail Gorbunov, Maxim Rakhuba
Convolutional Layer Convolution Kernel Upper Bound Convolution Operation Convolutional Architecture Spectral Norm

September 17, 2024

SDP: Spiking Diffusion Policy for Robotic Manipulation with Learnable Channel-Wise Membrane Thresholds
Zhixing Hou, Maoxu Gao, Hang Yu, Mengyu Yang, Chio-In Ieong
Spiking Neural Network Robotic Manipulation Convolution Operation Spiking Neuron P System Policy Diffusion Spiking Diffusion

September 6, 2024

Cycle Pixel Difference Network for Crisp Edge Detection
Changsong Liu, Wei Zhang, Yanyan Liu, Mingyang Li, Wenlin Li, Yimeng Fan, Xiangnan Bai, Liang Zhangd
Computer Vision Edge Detection Convolution Operation Recent Deep Learning Pixel Difference

July 15, 2024

ConvBench: A Comprehensive Benchmark for 2D Convolution Primitive Evaluation
Lucas Alvarenga, Victor Ferrari, Rafael Souza, Marcio Pereira, Guido Araujo
Comprehensive Benchmark Convolution Operation Learning Benchmark Convolution Technique Convolution Head Convolution Primitive

July 3, 2024

SFC: Achieve Accurate Fast Convolution under Low-precision Arithmetic
Liulu He, Yufei Zhao, Rui Gao, Yuan Du, Li Du
Direct Convolution Low Precision Convolution Operation Fast Convolution

April 26, 2024

Image Copy-Move Forgery Detection via Deep PatchMatch and Pairwise Ranking Learning
Yuanman Li, Yingjie He, Changsheng Chen, Li Dong, Bin Li, Jiantao Zhou, Xia Li
Convolution Operation Pairwise Ranking Copy Move Forgery Deep Cross Scale PatchMatch

April 17, 2024

Achieving Rotation Invariance in Convolution Operations: Shifting from Data-Driven to Mechanism-Assured
Hanlin Mo, Guoying Zhao
Data Driven Convolution Operation Rotation Invariant Rotation Invariance CNN Backbone

January 29, 2024

TFDMNet: A Novel Network Structure Combines the Time Domain and Frequency Domain Features
Hengyue Pan, Yixin Chen, Zhiliang Tian, Peng Qiao, Linbo Qiao, Dongsheng Li
Convolutional Neural Network Convolution Layer Time Frequency Frequency Domain Convolution Operation Unknown Network

January 10, 2024

Transformer-CNN Fused Architecture for Enhanced Skin Lesion Segmentation
Siddharth Tiwari
Convolutional Neural Network Medical Image Segmentation Skin Lesion Segmentation Convolution Operation Transformer Fusion

September 19, 2023

Multi-Context Dual Hyper-Prior Neural Image Compression
Atefeh Khoshkhahtinat, Ali Zafari, Piyush M. Mehta, Mohammad Akyash, Hossein Kashiani, Nasser M. Nasrabadi
Image Compression Convolution Operation Convolutional Transformer Learning Based Image Compression Deep Learning Based Video Compression Nonlinear Transform

September 12, 2023

DSLOT-NN: Digit-Serial Left-to-Right Neural Network Accelerator
Muhammad Sohail Ibrahim, Muhammad Usman, Malik Zohaib Nisar, Jeong-A Lee
Deep Neural Network Low Latency Convolution Operation Sequential Pattern Neural Network Accelerator

August 22, 2023

SPANet: Frequency-balancing Token Mixer using Spectral Pooling Aggregation Modulation
Guhnoo Yun, Juhan Yoo, Kijung Kim, Jeongho Lee, Dong Hwan Kim
Direct Convolution Convolution Operation Token Mixer Low Pas Balanced Representation

August 12, 2023

On the Interplay of Convolutional Padding and Adversarial Robustness
Paul Gavrikov, Janis Keuper
Convolutional Neural Network Adversarial Attack Adversarial Robustness Convolution Operation Zero Padding Edge Image

July 24, 2023

Entropy Transformer Networks: A Learning Approach via Tangent Bundle Data Manifold
Pourya Shamsolmoali, Masoumeh Zareapoor
CNN Architecture Convolution Operation Image Transformation Spatial Transformer Network Learning Approach Interpolation Method Tangent Bundle Transformer Based Entropy Model

June 29, 2023

Performance Analysis of DNN Inference/Training with Convolution and non-Convolution Operations
Hadi Esmaeilzadeh, Soroush Ghodrati, Andrew B. Kahng, Sean Kinzer, Susmita Dey Manasi, Sachin S. Sapatnekar, Zhiang Wang
Training Data Direct Convolution Convolution Layer Performance Analysis Convolution Operation DNN Inference Systolic Array

June 7, 2023

TEC-Net: Vision Transformer Embrace Convolutional Neural Networks for Medical Image Segmentation
Rui Sun, Tao Lei, Weichuan Zhang, Yong Wan, Yong Xia, Asoke K. Nandi
Convolutional Neural Network Vision Transformer Medical Image Segmentation Convolution Operation

June 5, 2023

Image Reconstruction for Accelerated MR Scan with Faster Fourier Convolutional Neural Networks
Xiaohan Liu, Yanwei Pang, Xuebin Sun, Yiming Liu, Yonghong Hou, Zhenchang Wang, Xuelong Li
Image Reconstruction Receptive Field Convolution Operation Accelerated MRI Fast Fourier Convolution

April 8, 2023

Arithmetic Intensity Balancing Convolution for Hardware-aware Efficient Block Design
Shinkook Choi, Junkyeong Choi
Neural Network Direct Convolution Convolution Operation Intensity Confusion Recent Deep Learning AI Accelerator

Convolution Operation

Papers

SparseTem: Boosting the Efficiency of CNN-Based Video Encoders by Exploiting Temporal Continuity

Med-IC: Fusing a Single Layer Involution with Convolutions for Enhanced Medical Image Classification and Segmentation

Tight and Efficient Upper Bound on Spectral Norm of Convolutional Layers

SDP: Spiking Diffusion Policy for Robotic Manipulation with Learnable Channel-Wise Membrane Thresholds

Cycle Pixel Difference Network for Crisp Edge Detection

ConvBench: A Comprehensive Benchmark for 2D Convolution Primitive Evaluation

SFC: Achieve Accurate Fast Convolution under Low-precision Arithmetic

Image Copy-Move Forgery Detection via Deep PatchMatch and Pairwise Ranking Learning

Achieving Rotation Invariance in Convolution Operations: Shifting from Data-Driven to Mechanism-Assured

TFDMNet: A Novel Network Structure Combines the Time Domain and Frequency Domain Features

Transformer-CNN Fused Architecture for Enhanced Skin Lesion Segmentation

Multi-Context Dual Hyper-Prior Neural Image Compression

DSLOT-NN: Digit-Serial Left-to-Right Neural Network Accelerator

SPANet: Frequency-balancing Token Mixer using Spectral Pooling Aggregation Modulation

On the Interplay of Convolutional Padding and Adversarial Robustness

Entropy Transformer Networks: A Learning Approach via Tangent Bundle Data Manifold

Performance Analysis of DNN Inference/Training with Convolution and non-Convolution Operations

TEC-Net: Vision Transformer Embrace Convolutional Neural Networks for Medical Image Segmentation

Image Reconstruction for Accelerated MR Scan with Faster Fourier Convolutional Neural Networks

Arithmetic Intensity Balancing Convolution for Hardware-aware Efficient Block Design