CNN Architecture

Convolutional Neural Networks (CNNs) are a cornerstone of computer vision, aiming to efficiently extract features from images for tasks like classification and object detection. Current research focuses on improving CNN efficiency through architectural innovations like structured ternary patterns, dynamic channel sampling, and novel pooling methods, as well as exploring the integration of CNNs with transformers to leverage both inductive biases and global context. These advancements are crucial for deploying CNNs on resource-constrained devices and enhancing their performance in various applications, from medical imaging to autonomous driving.

Papers

November 3, 2024

Optimizing Gastrointestinal Diagnostics: A CNN-Based Model for VCE Image Classification
Vaneeta Ahlawat, Rohit Sharma, Urush
Classification Code CNN Architecture Multiclass Classification 3D Capsule Capsule Endoscopy Gastrointestinal Tract Gastrointestinal Disease Detection

October 22, 2024

Development of CNN Architectures using Transfer Learning Methods for Medical Image Classification
Ganga Prasad Basyal, David Zeng, Bhaskar Pm Rimal
Convolutional Neural Network Deep Learning Model Transfer Learning State of the Art Development Activity Medical Image Classification CNN Architecture

September 18, 2024

On Vision Transformers for Classification Tasks in Side-Scan Sonar Imagery
BW Sheffield, Jeffrey Ellen, Ben Whitmore
Convolutional Neural Network Vision Transformer Classification Task CNN Architecture Seafloor Image Side Scan Sonar

July 30, 2024

DeepBaR: Fault Backdoor Attack on Deep Neural Network Layers
C. A. Martínez-Mejía, J. Solano, J. Breier, D. Bucko, X. Hou
Adversarial Sample CNN Architecture Neural Network Layer Backdoor Injection Fault Injection Attack Deep Attack

July 23, 2024

Image Classification using Fuzzy Pooling in Convolutional Kolmogorov-Arnold Networks
Ayan Igali, Pakizar Shamoi
Convolutional Neural Network Deep Learning Model Image Classification Kolmogorov Arnold Network CNN Architecture

July 20, 2024

Toward Efficient Convolutional Neural Networks With Structured Ternary Patterns
Christos Kyrkou
Convolutional Neural Network CNN Architecture High Performing 1D ConvNet

July 18, 2024

DuoFormer: Leveraging Hierarchical Visual Representations by Local and Global Attention
Xiaoya Tang, Bodong Zhang, Beatrice S. Knudsen, Tolga Tasdizen
Convolutional Neural Network Vision Transformer Global Attention CNN Architecture Hierarchical Transformer Hierarchical Representation

June 28, 2024

Explainable Image Captioning using CNN- CNN architecture and Hierarchical Attention
Rishi Kesav Mohan, Sanjay Sureshkumar, Vignesh Sivasubramaniam
Explainable AI High Explainability Image Captioning CNN Architecture Hierarchical Attention Caption Generation Convolutional Decoder

June 20, 2024

LeYOLO, New Scalable and Efficient CNN Architecture for Object Detection
Lilian Hollard, Lucas Mohimont, Nathalie Gaveau, Luiz-Angelo Steffenel
Neural Network Object Detection Potential Scalability CNN Architecture Pyramid Network Efficient Object Detection

June 16, 2024

Pick-or-Mix: Dynamic Channel Sampling for ConvNets
Ashish Kumar, Daneul Kim, Jaesik Park, Laxmidhar Behera
CNN Architecture High Performing 1D ConvNet Channel Pruning 1D Convolution Channel Sampling

June 12, 2024

KernelWarehouse: Rethinking the Design of Dynamic Convolution
Chao Li, Anbang Yao
Product Design CNN Architecture High Performing 1D ConvNet Kernel Extension Dynamic Convolution

June 1, 2024

Phasor-Driven Acceleration for FFT-based CNNs
Eduardo Reis, Thangarajah Akilan, Mohammed Khalid
Convolutional Neural Network CNN Architecture Fast Fourier Transform Transformer Accelerator

May 5, 2024

Jointly Learning Spatial, Angular, and Temporal Information for Enhanced Lane Detection
Muhammad Zeshan Alam
Temporal Information Light Field Lane Detection CNN Architecture Spatial Learning

April 24, 2024

April 15, 2024

WiTUnet: A U-Shaped Architecture Integrating CNN and Transformer for Improved Feature Alignment and Local Information Fusion
Bin Wang, Fei Deng, Peifan Jiang, Shuang Wang, Xiao Han, Zhixuan Zhang
Transformer Based CNN Architecture Feature Alignment Low Dose Low Dose Computed Tomography Skip Connection Global Local

March 12, 2024

PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution
Honghao Chen, Xiangxiang Chu, Yongjian Ren, Xin Zhao, Kaiqi Huang
CNN Architecture Large Kernel Mobile Convolution

February 23, 2024

A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends
Abolfazl Younesi, Mohsen Ansari, MohammadAmin Fazli, Alireza Ejlali, Muhammad Shafique, Jörg Henkel
Deep Learning Convolutional Neural Network Technical Challenge Financial Application Direct Convolution CNN Architecture Future Trend Different Convolutional Neural Network 3D Convolutional Neural Network

February 19, 2024

Stealing the Invisible: Unveiling Pre-Trained CNN Models through Adversarial Examples and Timing Side-Channels
Shubhi Shukla, Manaar Alam, Pabitra Mitra, Debdeep Mukhopadhyay
Adversarial Example Transfer Learning Generative Adversarial CNN Architecture Convolutional Neural Network Model Adversarial Image Side Channel

February 13, 2024

Peeking Behind the Curtains of Residual Learning
Tunhou Zhang, Feng Yan, Hai Li, Yiran Chen
CNN Architecture Residual Connection Residual Learning Light Curtain Plain Neural

CNN Architecture

Papers

Optimizing Gastrointestinal Diagnostics: A CNN-Based Model for VCE Image Classification

Development of CNN Architectures using Transfer Learning Methods for Medical Image Classification

On Vision Transformers for Classification Tasks in Side-Scan Sonar Imagery

DeepBaR: Fault Backdoor Attack on Deep Neural Network Layers

Image Classification using Fuzzy Pooling in Convolutional Kolmogorov-Arnold Networks

Toward Efficient Convolutional Neural Networks With Structured Ternary Patterns

DuoFormer: Leveraging Hierarchical Visual Representations by Local and Global Attention

Explainable Image Captioning using CNN- CNN architecture and Hierarchical Attention

LeYOLO, New Scalable and Efficient CNN Architecture for Object Detection

Pick-or-Mix: Dynamic Channel Sampling for ConvNets

KernelWarehouse: Rethinking the Design of Dynamic Convolution

Phasor-Driven Acceleration for FFT-based CNNs

Jointly Learning Spatial, Angular, and Temporal Information for Enhanced Lane Detection

Perception and Localization of Macular Degeneration Applying Convolutional Neural Network, ResNet and Grad-CAM

Understanding and Improving CNNs with Complex Structure Tensor: A Biometrics Study

WiTUnet: A U-Shaped Architecture Integrating CNN and Transformer for Improved Feature Alignment and Local Information Fusion

PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution

A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends

Stealing the Invisible: Unveiling Pre-Trained CNN Models through Adversarial Examples and Timing Side-Channels

Peeking Behind the Curtains of Residual Learning