Robust Convolutional Neural Network

Robust Convolutional Neural Networks (CNNs) aim to improve the reliability and resilience of CNNs against various challenges, such as adversarial attacks, noisy data, and variations in input conditions (e.g., lighting, image distortions). Current research focuses on enhancing robustness through techniques like feature masking, efficient adversarial training methods, and incorporating biologically-inspired pre-processing steps (e.g., steerable pyramid transforms) or modular network designs. These advancements are crucial for deploying CNNs in real-world applications where robustness is paramount, improving the reliability of AI systems in critical domains like medical image analysis and autonomous driving.

Papers

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 24, 2023

Breaking of brightness consistency in optical flow with a lightweight CNN network
Yicheng Lin, Shuo Wang, Yunlong Jiang, Bin Han
Optical Flow Important News Lightweight CNN Robust Convolutional Neural Network Sparse Optical Flow

November 24, 2022

Semantic Communication Enabling Robust Edge Intelligence for Time-Critical IoT Applications
Andrea Cavagna, Nan Li, Alexandros Iosifidis, Qi Zhang
Semantic Communication Edge Intelligence Robust Convolutional Neural Network

September 11, 2022

Patching Weak Convolutional Neural Network Models through Modularization and Composition
Binhang Qi, Hailong Sun, Xiang Gao, Hongyu Zhang
Convolutional Neural Network Model Modularity Function Compositional Ability Robust Convolutional Neural Network

July 21, 2022

Towards Efficient Adversarial Training on Vision Transformers
Boxi Wu, Jindong Gu, Zhifeng Li, Deng Cai, Xiaofei He, Wei Liu
Generative Adversarial Network Vision Transformer Fast Adversarial Training Efficient Adversarial Training Robust Convolutional Neural Network

May 25, 2022

How explainable are adversarially-robust CNNs?
Mehdi Nourelahi, Lars Kotthoff, Peijie Chen, Anh Nguyen
Convolutional Neural Network Adversarial Robustness CNN Architecture Better Explainability Robust Convolutional Neural Network

March 7, 2022

L2CS-Net: Fine-Grained Gaze Estimation in Unconstrained Environments
Ahmed A. Abdelrahman, Thorsten Hempel, Aly Khalifa, Ayoub Al-Hamadi
Gaze Direction Gaze Annotation Human Gaze Unconstrained Environment Robust Convolutional Neural Network

February 15, 2022

A precortical module for robust CNNs to light variations
R. Fioresi, J. Petkovic
Visual Cortex Brightness Variation Convolutional Module Robust Convolutional Neural Network Ventral Visual

February 9, 2022

January 20, 2022

Steerable Pyramid Transform Enables Robust Left Ventricle Quantification
Xiangyang Zhu, Kede Ma, Wufeng Xue
Ventricle Segmentation Left Ventricular Pyramid Vision Transformer Robust Feature Robust Convolutional Neural Network Robustness Measurement

Robust Convolutional Neural Network

Papers

Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Masking

Breaking of brightness consistency in optical flow with a lightweight CNN network

Semantic Communication Enabling Robust Edge Intelligence for Time-Critical IoT Applications

Patching Weak Convolutional Neural Network Models through Modularization and Composition

Towards Efficient Adversarial Training on Vision Transformers

How explainable are adversarially-robust CNNs?

L2CS-Net: Fine-Grained Gaze Estimation in Unconstrained Environments

A precortical module for robust CNNs to light variations

Optimal Hyperparameters and Structure Setting of Multi-Objective Robust CNN Systems via Generalized Taguchi Method and Objective Vector Norm

Learning Robust Convolutional Neural Networks with Relevant Feature Focusing via Explanations

Steerable Pyramid Transform Enables Robust Left Ventricle Quantification