Robust Classification

Robust classification aims to develop machine learning models that maintain high accuracy even when faced with noisy, incomplete, or adversarially perturbed data. Current research focuses on improving model robustness through techniques like novel loss functions (e.g., bounded loss functions), data augmentation strategies (e.g., label smoothing, image noising), and architectural innovations (e.g., attractor networks, diffusion models, and brain-inspired architectures). These advancements are crucial for deploying reliable machine learning systems in real-world applications where data quality is often imperfect, impacting fields ranging from medical image analysis to autonomous driving.

Papers

August 7, 2022

On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks
Laura Fee Nern, Harsh Raj, Maurice Georgi, Yash Sharma
Native Robustness Adversarial Robustness Formality Transfer Downstream Task Robust Classification Downstream Forecasting Task

July 24, 2022

Can we achieve robustness from data alone?
Nikolaos Tsilivis, Jingtong Su, Julia Kempe
Adversarial Attack Native Robustness Raw Data Meta Learning Robust Classification Standard Gradient Descent

July 20, 2022

Towards Accurate and Robust Classification in Continuously Transitioning Industrial Sprays with Mixup
Hongjiang Li, Huanyi Shui, Alemayehu Admasu, Praveen Narayanan, Devesh Upadhyay
Neural Network Deep Neural Network Data Augmentation Image Classification Spatio Temporal Mixup Mechanism Federat\textbf{T}ed Cl\textbf{A}ss Continual Lea\textbf{R}nin\textbf{G Robust Classification Chemical Spray

May 17, 2022

Monotonicity Regularization: Improved Penalties and Novel Applications to Disentangled Representation Learning and Robust Classification
Joao Monteiro, Mohamed Osama Ahmed, Hossein Hajimirsadeghi, Greg Mori
Generative Modeling Disentangled Representation Robust Classification Risk Minimization Partial Monotonicity Novel Application Penalty Method Monotonic Neural Network Appropriate Penalty Term

May 2, 2022

MIRST-DM: Multi-Instance RST with Drop-Max Layer for Robust Classification of Breast Cancer
Shoukun Sun, Min Xian, Aleksandar Vakanski, Hossny Ghanem
Adversarial Robustness Breast Cancer Robust Classification Adversarial Instance Dropout Layer Robust Self

May 1, 2022

DDDM: a Brain-Inspired Framework for Robust Classification
Xiyuan Chen, Xingyu Li, Yi Zhou, Tianming Yang
Adversarial Attack Adversarial Perturbation Robust Classification Drift Diffusion Evidence Accumulation

March 22, 2022

Robust Classification using Contractive Hamiltonian Neural ODEs
Muhammad Zakwan, Liang Xu, Giancarlo Ferrari-Trecate
Native Robustness Neural ODE Robust Classification Input Perturbation

January 23, 2022

Efficient and Robust Classification for Sparse Attacks
Mark Beliaev, Payam Delgosha, Hamed Hassani, Ramtin Pedarsani
High Efficiency Adversarial Training Defense Method Robust Classification Sparse Attack \Ell_1$ Norm

January 12, 2022

Adversarially Robust Classification by Conditional Generative Model Inversion
Mitra Alirezaei, Tolga Tasdizen
Adversarial Attack Generative Adversarial Network Adversarial Training Gradient Based Attack Robust Classification Adversarial Defense Generative Model Inversion

January 9, 2022

Robust classification with flexible discriminant analysis in heterogeneous data
Pierre Houdouin, Frédéric Pascal, Matthieu Jonckheere, Andrew Wang
Heterogeneous Data Maximum Likelihood Cyclic Symmetry Discriminant Analysis Non Gaussian Robust Classification Robust Principal Component Analysis Quadratic Discriminant Analysis

December 31, 2021

Benign Overfitting in Adversarially Robust Linear Classification
Jinghui Chen, Yuan Cao, Quanquan Gu
Adversarial Example Adversarial Training Adversarial Perturbation Benign Overfitting Adversarial Risk Robust Classification

December 18, 2021

3D Structural Analysis of the Optic Nerve Head to Robustly Discriminate Between Papilledema and Optic Disc Drusen
Michaël J. A. Girard, Satish K. Panda, Tin Aung Tun, Elisabeth A. Wibroe, Raymond P. Najjar, Aung Tin, Alexandre H. Thiéry, Steffen Hamann, Clare Fraser, Dan Milea
Optical Coherence Tomography 3D Structure Robust Classification Tissue Image Optic Nerve Head Explainable Papilledema Indicator

December 13, 2021

Long-tail Recognition via Compositional Knowledge Transfer
Sarah Parisot, Pedro M. Esperanca, Steven McDonagh, Tamas J. Madarasz, Yongxin Yang, Zhenguo Li
Tail Class Robust Classification Long Tail Recognition Free Knowledge Transfer