Deep Learning Classification

Deep learning classification aims to build accurate and reliable models that categorize data into predefined classes. Current research emphasizes improving model interpretability, particularly by analyzing decision boundaries and developing methods for uncertainty quantification, often employing convolutional neural networks (CNNs), recurrent neural networks (RNNs like LSTMs), and ensemble methods. These advancements are crucial for deploying deep learning in high-stakes applications like medical diagnosis and autonomous systems, where understanding model behavior and quantifying uncertainty are paramount for responsible use. Furthermore, research focuses on mitigating issues like spurious correlations and class imbalance to enhance model robustness and generalization.

Papers

October 31, 2024

Using Deep Neural Networks to Quantify Parking Dwell Time
Marcelo Eduardo Marques Ribas (1), Heloisa Benedet Mendes (1), Luiz Eduardo Soares de Oliveira (1), Luiz Antonio Zanlorensi (2), Paulo Ricardo Lisboa de Almeida (1) ((1) Department of Informatics - Federal University of Paraná, (2) DeepNeuronic)
Deep Neural Network Deep Learning Classification Parking Space Dwell Time

October 12, 2024

C-Adapter: Adapting Deep Classifiers for Efficient Conformal Prediction Sets
Kangdao Liu, Hao Zeng, Jianguo Huang, Huiping Zhuang, Chi-Man Vong, Hongxin Wei
Conformal Prediction Tiny Set Deep Learning Classification Conformal Predictor Optimal Prediction Tip Adapter

August 12, 2024

Finding Patterns in Ambiguity: Interpretable Stress Testing in the Decision~Boundary
Inês Gomes, Luís F. Teixeira, Jan N. van Rijn, Carlos Soares, André Restivo, Luís Cunha, Moisés Santos
Deep Learning Inherent Interpretability Pattern Recognition Decision Boundary Structural Ambiguity Post Hoc Deep Learning Classification Stress Testing

August 3, 2024

Comparison of Embedded Spaces for Deep Learning Classification
Stefan Scholl
Deep Learning Loss Function Consistent Comparison Open Set Recognition Deep Learning Classification Embedded Space

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 Deep Neural Network Classifier Evidential Uncertainty Surprisal Theory

May 23, 2024

Deep Learning Classification of Photoplethysmogram Signal for Hypertension Levels
Nida Nasir, Mustafa Sameer, Feras Barneih, Omar Alshaltone, Muneeb Ahmed
LSTM Network Time Frequency PPG Signal LSTM Model Blood Pressure Deep Learning Classification Photoplethysmography Signal

April 16, 2024

CNN-based explanation ensembling for dataset, representation and explanations evaluation
Weronika Hryniewska-Guzik, Luca Longo, Przemysław Biecek
Data Set Deep Convolutional Neural Network Line by Line Explanation Explainable Artificial Intelligence Individual Representation Deep Learning Classification Complex Deep Explanation Evaluation

March 13, 2024

Reduced Jeffries-Matusita distance: A Novel Loss Function to Improve Generalization Performance of Deep Classification Models
Mohammad Lashkari, Amin Gheibi
Deep Neural Network Loss Function Generalization Performance Deep Learning Classification Mahalanobis Distance

February 25, 2024

On the Feasibility of Deep Learning Classification from Raw Signal Data in Radiology, Ultrasonography and Electrophysiology
Szilard Enyedi
Neural Network Deep Learning Medical Imaging Radiology Imaging Deep Learning Classification Electrophysiological Data Deep Learning Solution

February 23, 2024

Calibration of Deep Learning Classification Models in fNIRS
Zhihao Cao, Zizhou Luo
Calibration Performance Deep Learning Classification Functional Near Infrared Spectroscopy fNIRS Signal

February 21, 2024

Robustness of Deep Neural Networks for Micro-Doppler Radar Classification
Mikolaj Czerkawski, Carmine Clemente, Craig Michie, Christos Tachtatzis
Deep Neural Network Native Robustness Adversarial Example Fully Convolutional Deep Learning Classification Micro Doppler Radar Processing

February 8, 2024

On Calibration and Conformal Prediction of Deep Classifiers
Lahav Dabah, Tom Tirer
Conformal Prediction Calibration Performance Softmax Function Adaptive Method Temperature Scaling Deep Learning Classification

January 30, 2024

Category-wise Fine-Tuning: Resisting Incorrect Pseudo-Labels in Multi-Label Image Classification with Partial Labels
Chak Fong Chong, Xinyi Fang, Jielong Guo, Yapeng Wang, Wei Ke, Chan-Tong Lam, Sio-Kei Im
Fine Tuning Pseudo Label Multi Label Image Classification Deep Learning Classification Partial Label Well Trained Model

December 4, 2023

STADEE: STAtistics-based DEEp Detection of Machine Generated Text
Zheng Chen, Huming Liu
Pre Trained Language Model Machine Generated Deep Learning Classification Arena Hard Statistical Feature

October 10, 2023

Conformal Prediction for Deep Classifier via Label Ranking
Jianguo Huang, Huajun Xi, Linjun Zhang, Huaxiu Yao, Yue Qiu, Hongxin Wei
Conformal Prediction Prediction Set Deep Learning Classification Training Label Adaptive Prediction

October 9, 2023

Quantifying Uncertainty in Deep Learning Classification with Noise in Discrete Inputs for Risk-Based Decision Making
Maryam Kheirandish, Shengfan Zhang, Donald G. Catanzaro, Valeriu Crudu
Uncertainty Quantification Industrial Disturbing Noise Risk Prediction Bayesian Deep Learning Prediction Uncertainty Deep Learning Classification Risk Based Decision

August 30, 2023

Early Detection of Red Palm Weevil Infestations using Deep Learning Classification of Acoustic Signals
Wadii Boulila, Ayyub Alzahem, Anis Koubaa, Bilel Benjdira, Adel Ammar
Data Detection Early Detection Deep Learning Classification Acoustic Signal Red Palm Weevil

July 6, 2023

The Role of Subgroup Separability in Group-Fair Medical Image Classification
Charles Jones, Mélanie Roschewitz, Ben Glocker
Integral Role Algorithmic Bias Deep Learning Classification Performance Disparity Subgroup Performance

June 3, 2023

Deep Classifier Mimicry without Data Access
Steven Braun, Martin Mundt, Kristian Kersting
Pre Trained Model Information Access Deep Learning Classification Task Agnostic Distillation Abductive Learning

May 23, 2023

Gaussian Latent Representations for Uncertainty Estimation using Mahalanobis Distance in Deep Classifiers
Aishwarya Venkataramanan, Assia Benbihi, Martin Laviale, Cedric Pradalier
Uncertainty Estimation Deep Learning Classification Mahalanobis Distance Classification Uncertainty Gaussian Latent Gaussian Representation