Data to 14 Oct 2026

Effects of Degradations on Deep Neural Network Architectures

arXiv 1807.10108 ↗First posted 26 Jul 2018cs.CV eess.IVcited by 48

Not on the map. Why?

Abstract (arXiv)

Deep convolutional neural networks (CNN) have massively influenced recent advances in large-scale image classification. More recently, a dynamic routing algorithm with capsules (groups of neurons) has shown state-of-the-art recognition performance. However, the behavior of such networks in the presence of a degrading signal (noise) is mostly unexplored. An analytical study on different network architectures toward noise robustness is essential for selecting the appropriate model in a specific application scenario. This paper presents an extensive performance analysis of six deep architectures for image classification on six most common image degradation models. In this study, we have compared VGG-16, VGG-19, ResNet-50, Inception-v3, MobileNet and CapsuleNet architectures on Gaussian white, Gaussian color, salt-and-pepper, Gaussian blur, motion blur and JPEG compression noise models.

Key facts. Cited by 48 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 14; 2022: 3; 2023: 9; 2024: 7; 2025: 10; 2026: 5.

48 papers.

Sort:

By area:

2021Online Continual Learning in Image Classification: An Empirical Surveycited by 245
2021Towards Causal Representation Learningcited by 209
2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 99
2021Visual Representation Learning Does Not Generalize Strongly Within the Same Domaincited by 61
2022Assaying Out-Of-Distribution Generalization in Transfer Learningcited by 53
2021Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorizationcited by 52
2021Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restorationcited by 50
2023Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learningcited by 40
2024Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversitycited by 30
2022Integrative conformal p-values for powerful out-of-distribution testing with labeled outlierscited by 19
2023Joint Task and Data Oriented Semantic Communications: A Deep Separate Source-channel Coding Schemecited by 19
2023Confidence-aware Personalized Federated Learning via Variational Expectation Maximizationcited by 17

36 more

2021The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agentscited by 12
2025Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learningcited by 12
2024DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devicescited by 9
2023Handling Data Heterogeneity via Architectural Design for Federated Visual Recognitioncited by 8
2025Toward Robust Non-Transferable Learning: A Survey and Benchmarkcited by 7
2021AQuA: Analytical Quality Assessment for Optimizing Video Analytics Systemscited by 6
2025When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Needcited by 5
2021W2WNet: a two-module probabilistic Convolutional Neural Network with embedded data cleansing functionalitycited by 3
2021Learning Fuzzy Clustering for SPECT/CT Segmentation via Convolutional Neural Networkscited by 3
2021Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networkscited by 3
2021Geometric feature performance under downsampling for EEG classification taskscited by 2
2021A Novel lightweight Convolutional Neural Network, ExquisiteNetV2cited by 2
2022Impact of Video Compression on the Performance of Object Detection Systems for Surveillance Applicationscited by 2
2023Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenescited by 2
2024Towards Federated Domain Unlearning: Verification Methodologies and Challengescited by 2
2021Learning degraded image classification with restoration data fidelitycited by 1
2023What's color got to do with it? Face recognition in grayscalecited by 1
2024Pre-Trained Model Recommendation for Downstream Fine-tuningcited by 1
2024Clarifying Myths About the Relationship Between Shape Bias, Accuracy, and Robustnesscited by 1
2025Mitigating Domain Shift in Federated Learning via Intra- and Inter-Domain Prototypescited by 1
2026Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuningcited by 1
2026Distribution Alignment for One-Shot Federated Learning via Optimal Transportcited by 1
2021A Structured Analysis of the Video Degradation Effects on the Performance of a Machine Learning-enabled Pedestrian Detectorcited by 0
2023Deep Learning Based Object Tracking in Walking Droplet and Granular Intruder Experimentscited by 0
2023How much data do I need? A case study on medical datacited by 0
2024Partially Recentralization Softmax Loss for Vision-Language Models Robustnesscited by 0
2024Overcoming Data Inequality across Domains with Semi-Supervised Domain Generalizationcited by 0
2025Robust Federated Learning on Edge Devices with Domain Heterogeneitycited by 0
2025SNAP: A Benchmark for Testing the Effects of Capture Conditions on Fundamental Vision Taskscited by 0
2025Calibrating Biased Distribution in VFM-derived Latent Space via Cross-Domain Geometric Consistencycited by 0
2025Incorporating Visual Cortical Lateral Connection Properties into CNN: Recurrent Activation and Excitatory-Inhibitory Separationcited by 0
2025Personalized federated prototype learning in mixed heterogeneous data scenarioscited by 0
2025Hierarchical Dataset Selection for High-Quality Data Sharingcited by 0
2026Trust-Aware Joint Feature-Prediction Discrepancy for Robust Domain Adaptationcited by 0
2026Hidden-Shot: Towards One-Shot Task Generalization for Low-Level Vision Generalist Modelscited by 0
2026Geometric Similarity in VLM Low-Level Vision Representationscited by 0