CNN Classifier

Convolutional Neural Networks (CNNs) are a cornerstone of image classification, aiming to accurately categorize images based on learned visual features. Current research emphasizes improving CNN accuracy, efficiency, and interpretability, exploring techniques like circular regression for precise directional estimations, and employing methods such as Grad-CAM and StyleGAN inversion for enhanced explainability and concept-based analysis. These advancements are crucial for building trust in CNN classifiers, mitigating biases, and enabling their wider application in diverse fields, from medical image analysis to remote sensing.

Papers

October 26, 2024

Enhancing CNN Classification with Lamarckian Memetic Algorithms and Local Search
Akhilbaran Ghosh, Rama Sai Adithya Kalidindi
Deep Neural Network Optimization Purpose Local Search Classification Network Memetic Algorithm CNN Classifier Weight Optimization

June 27, 2024

Single Image Estimation of Cell Migration Direction by Deep Circular Regression
Lennart Bruns, Lucas Lamparter, Milos Galic, Xiaoyi Jiang
Single Image CNN Classifier Cell Migration Image Estimation

May 6, 2024

Interpretable Network Visualizations: A Human-in-the-Loop Approach for Post-hoc Explainability of CNN-based Image Classification
Matteo Bianchi, Antonio De Santis, Andrea Tocchetti, Marco Brambilla
Convolutional Neural Network Image Classification Constructive Approach High Explainability Saliency Map Post Hoc Explainability CNN Classifier

March 25, 2024

On the rates of convergence for learning with convolutional neural networks
Yunfei Yang, Han Feng, Ding-Xuan Zhou
Neural Network Convolutional Neural Network Early Stage Convergence Convergence Rate Universal Rate CNN Classifier

March 21, 2024

Raw Instinct: Trust Your Classifiers and Skip the Conversion
Christos Kantas, Bjørk Antoniussen, Mathias V. Andersen, Rasmus Munksø, Shobhit Kotnala, Simon B. Jensen, Andreas Møgelmose, Lau Nørgaard, Thomas B. Moeslund
Simple Classifier RGB Image Automated Conversion Raw Image Skip and Recover CNN Classifier

October 12, 2023

Strategies and impact of learning curve estimation for CNN-based image classification
Laura Didyk, Brayden Yarish, Michael A. Beck, Christopher P. Bidinosti, Christopher J. Henry
Training Data Machine Learning Model Global Impact General Strategy Image Classification Task Learning Curve CNN Classifier Curve Modeling

February 23, 2023

FG-SSA: Features Gradient-based Signals Selection Algorithm of Linear Complexity for Convolutional Neural Networks
Yuto Omae, Yusuke Sakai, Hirotaka Takahashi
Convolutional Neural Network Feature Wise Linear Complexity CNN Classifier Gradient Conflict

January 16, 2023

Img2Tab: Automatic Class Relevant Concept Discovery from StyleGAN Features for Explainable Image Classification
Youngjae Song, Sung Kuk Shyn, Kwang-su Kim
Inherent Interpretability StyleGAN Latent Concept Based Concept Discovery Interpretable Image Tabular Data Classification CNN Classifier

October 28, 2022

Improving Chest X-Ray Classification by RNN-based Patient Monitoring
David Biesner, Helen Schneider, Benjamin Wulff, Ulrike Attenberger, Rafet Sifa
Chest X Ray Chest X Ray Image Chest Radiograph Chest X Ray Classification Patient Monitoring CNN Classifier

September 6, 2022

Task-wise Sampling Convolutions for Arbitrary-Oriented Object Detection in Aerial Images
Zhanchao Huang, Wei Li, Xiang-Gen Xia, Hao Wang, Ran Tao
Aerial Image Convolutional Kernel Point Based CNN Classifier Arbitrary Oriented Object DEtection

April 28, 2022

Automatic Machine Learning for Multi-Receiver CNN Technology Classifiers
Amir-Hossein Yazdani-Abyaneh, Marwan Krunz
Machine Learning Convolutional Neural Network Signal Classification CNN Classifier Wireless Infrastructure

April 20, 2022

Adversarial Scratches: Deployable Attacks to CNN Classifiers
Loris Giulivi, Malhar Jere, Loris Rossi, Farinaz Koushanfar, Gabriela Ciocarlie, Briland Hitaj, Giacomo Boracchi
Adversarial Example Black Box Attack CNN Classifier Adversarial Disturbance

April 14, 2022

Explainable Analysis of Deep Learning Methods for SAR Image Classification
Shenghan Su, Ziteng Cui, Weiwei Guo, Zenghui Zhang, Wenxian Yu
Deep Learning Explainable AI Synthetic Aperture Radar CNN Classifier

April 12, 2022

VisCUIT: Visual Auditor for Bias in CNN Image Classifier
Seongmin Lee, Zijie J. Wang, Judy Hoffman, Duen Horng Chau
Absolute Stance Bias CNN Classifier Bias Detection Method Classifier Performance

January 8, 2022

A Sneak Attack on Segmentation of Medical Images Using Deep Neural Network Classifiers
Shuyue Guan, Murray Loew
Medical Image Segmentation Based Approach Segmentation Model Segmentation Result Deep Learning Classifier Stealthy Attack CNN Classifier Location Heatmaps

December 9, 2021

Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers
Zunlei Feng, Jiacong Hu, Sai Wu, Xiaotian Yu, Jie Song, Mingli Song
Convolutional Neural Network Model Prediction Aggregated Gradient CNN Classifier

CNN Classifier

Papers

Enhancing CNN Classification with Lamarckian Memetic Algorithms and Local Search

Single Image Estimation of Cell Migration Direction by Deep Circular Regression

Interpretable Network Visualizations: A Human-in-the-Loop Approach for Post-hoc Explainability of CNN-based Image Classification

On the rates of convergence for learning with convolutional neural networks

Raw Instinct: Trust Your Classifiers and Skip the Conversion

Strategies and impact of learning curve estimation for CNN-based image classification

FG-SSA: Features Gradient-based Signals Selection Algorithm of Linear Complexity for Convolutional Neural Networks

Img2Tab: Automatic Class Relevant Concept Discovery from StyleGAN Features for Explainable Image Classification

Improving Chest X-Ray Classification by RNN-based Patient Monitoring

Task-wise Sampling Convolutions for Arbitrary-Oriented Object Detection in Aerial Images

Automatic Machine Learning for Multi-Receiver CNN Technology Classifiers

Adversarial Scratches: Deployable Attacks to CNN Classifiers

Explainable Analysis of Deep Learning Methods for SAR Image Classification

VisCUIT: Visual Auditor for Bias in CNN Image Classifier

A Sneak Attack on Segmentation of Medical Images Using Deep Neural Network Classifiers

Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers