CNN Framework

Convolutional Neural Networks (CNNs) are a fundamental deep learning architecture used for analyzing data with grid-like topology, such as images and videos. Current research focuses on improving CNN efficiency and robustness through techniques like hierarchical architectures, self-attention mechanisms, and novel loss functions tailored for specific tasks (e.g., ordinal regression, domain adaptation). These advancements aim to enhance accuracy, generalization, and resilience to adversarial attacks, leading to improved performance in diverse applications ranging from image classification and object detection to network security and crowd analysis. The resulting models are increasingly deployed on resource-constrained devices, driving innovation in edge AI.

Papers

September 1, 2024

A Novel Self-Attention-Enabled Weighted Ensemble-Based Convolutional Neural Network Framework for Distributed Denial of Service Attack Classification
Kanthimathi S, Shravan Venkatraman, Jayasankar K S, Pranay Jiljith T, Jashwanth R
Convolutional Neural Network Long Form Novel Distributed Denial of Service Attack Pattern CNN Framework

August 22, 2024

Deep Learning with CNNs: A Compact Holistic Tutorial with Focus on Supervised Regression (Preprint)
Yansel Gonzalez Tejeda, Helmut A. Mayer
Deep Learning Convolutional Neural Network Tutorial Review CNN Framework

July 31, 2024

SHA-CNN: Scalable Hierarchical Aware Convolutional Neural Network for Edge AI
Narendra Singh Dhakad, Yuvnish Malhotra, Santosh Kumar Vishvakarma, Kaushik Roy
Convolutional Neural Network CNN Model Edge AI CNN Framework

July 18, 2024

Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Masking
Yunpeng Gong, Chuangliang Zhang, Yongjie Hou, Lifei Chen, Min Jiang
Convolutional Neural Network Adversarial Attack Adversarial Robustness Structured Dropout Feature Masking Robust Convolutional Neural Network CNN Framework

October 11, 2023

A Novel Voronoi-based Convolutional Neural Network Framework for Pushing Person Detection in Crowd Videos
Ahmed Alia, Mohammed Maree, Mohcine Chraibi, Armin Seyfried
Long Form Novel Person Detection Scale Crowd Crowd Flow CNN Framework Crowd Management

November 17, 2022

DeepVoxNet2: Yet another CNN framework
Jeroen Bertels, David Robben, Robin Lemmens, Dirk Vandermeulen
Tumor Segmentation Segmentation Pipeline CNN Framework

May 22, 2022

OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation
Thanh-Dat Truong, Naga Venkata Sai Raviteja Chappa, Xuan Bac Nguyen, Ngan Le, Ashley Dowling, Khoa Luu
Domain Adaptation Optimal Transport Unsupervised Domain Adaptation Object Recognition Unsupervised Domain Adaption CNN Framework

May 10, 2022

THOR: Threshold-Based Ranking Loss for Ordinal Regression
Tzeviya Sylvia Fuchs, Joseph Keshet
Loss Function Ordinal Regression Supervised Classification Ranking Loss CNN Framework