Deep Neural Network Classifier

Deep neural network (DNN) classifiers are powerful tools for categorizing data, but their accuracy and robustness remain active research areas. Current efforts focus on improving evaluation methods, including data-less assessment of classifier quality and techniques for efficiently testing accuracy with limited labeled data, as well as enhancing robustness against adversarial attacks and distribution shifts. These advancements are crucial for deploying DNN classifiers reliably in safety-critical applications like autonomous systems and aviation, while also improving their generalizability and mitigating overfitting issues.

Papers

July 17, 2024

Novel Deep Neural Network Classifier Characterization Metrics with Applications to Dataless Evaluation
Nathaniel Dean, Dilip Sarkar
Deep Neural Network Financial Application Reference Free Evaluation Deep Neural Network Classifier

June 16, 2024

Evidential Uncertainty Sets in Deep Classifiers Using Conformal Prediction
Hamed Karimi, Reza Samavi
Conformal Prediction Evidential Deep Learning Deep Learning Classification Conformal Prediction Set Evidential Uncertainty Deep Neural Network Classifier Surprisal Theory

March 28, 2024

DeepSample: DNN sampling-based testing for operational accuracy assessment
Antonio Guerriero, Roberto Pietrantuono, Stefano Russo
Deep Neural Network Level Test DNN Accuracy Accuracy Measurement Deep Neural Network Classifier

January 8, 2024

Robustness Assessment of a Runway Object Classifier for Safe Aircraft Taxiing
Yizhak Elboher, Raya Elsaleh, Omri Isac, Mélanie Ducoffe, Audrey Galametz, Guillaume Povéda, Ryma Boumazouza, Noémie Cohen, Guy Katz
Deep Neural Network Native Robustness Robustness Evaluation Deep Neural Network Classifier Airport Runway Segmentation

November 23, 2023

Touch Analysis: An Empirical Evaluation of Machine Learning Classification Algorithms on Touch Data
Melodee Montgomery, Prosenjit Chatterjee, John Jenkins, Kaushik Roy
Empirical Evaluation Discriminant Analysis Machine Learning Classifier Naive Bayes Touch Sensor Deep Neural Network Classifier Touch Dynamic

September 28, 2023

Post-Training Overfitting Mitigation in DNN Classifiers
Hang Wang, David J. Miller, George Kesidis
Adversarial Training Adversarial Learning Model Overfitting Benign Overfitting Backdoor Poisoning Attack Deep Neural Network Classifier

August 15, 2023

A Review of Adversarial Attacks in Computer Vision
Yutong Zhang, Yao Li, Yin Li, Zhichang Guo
Adversarial Attack Computer Vision Adversarial Sample White Box Deep Neural Network Classifier

May 24, 2023

Fantastic DNN Classifiers and How to Identify them without Data
Nathaniel Dean, Dilip Sarkar
Adversarial Example Raw Data Generalization Performance Cross Entropy Loss Deep Neural Network Classifier

December 29, 2022

Detection of out-of-distribution samples using binary neuron activation patterns
Bartlomiej Olber, Krystian Radlak, Adam Popowicz, Michal Szczepankiewicz, Krystian Chachuła
Deep Neural Network Data Detection Distribution Detection Convolutional Layer Distribution Sample Deep Neural Network Classifier Binary Neuron

November 18, 2022

Invariant Learning via Diffusion Dreamed Distribution Shifts
Priyatham Kattakinda, Alexander Levine, Soheil Feizi
Image Classification Distribution Shift Background Generation Invariant Learning Deep Neural Network Classifier ImageNet Class

October 3, 2022

Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems
Jirong Yi, Qiaosheng Zhang, Zhen Chen, Qiao Liu, Wei Shao
Deep Neural Network Mutual Information Cross Entropy Loss Information Theoretic Cross Entropy Training Deep Deep Neural Network Classifier

September 5, 2022

A Principled Evaluation Protocol for Comparative Investigation of the Effectiveness of DNN Classification Models on Similar-but-non-identical Datasets
Esla Timothy Anzaku, Haohan Wang, Arnout Van Messem, Wesley De Neve
Deep Neural Network Comparative Study Benchmark Datasets ImageNet Dataset Evaluation Framework Deep Neural Network Classifier Dataset Similarity

August 31, 2022

Unrestricted Adversarial Samples Based on Non-semantic Feature Clusters Substitution
MingWei Zhou, Xiaobing Pei
Adversarial Example Adversarial Sample Semantic Feature Defense Method Deep Neural Network Classifier Unrestricted Adversarial

April 30, 2022

DIRA: Dynamic Domain Incremental Regularised Adaptation
Abanoub Ghobrial, Xuan Zheng, Darryl Hond, Hamid Asgari, Kerstin Eder
Deep Neural Network Domain Adaptive Deep Neural Network Classifier Imagenet C Dynamic Incremental Regularised Adaptation