# Effects of Degradations on Deep Neural Network Architectures

arXiv: https://arxiv.org/abs/1807.10108 · HTML: https://mlsanity.com/paper/1807.10108/

## Key facts

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

## Built on by (most cited first, 30 of 48)

- [Online Continual Learning in Image Classification: An Empirical Survey](https://mlsanity.com/paper/2101.10423/) (2021)
- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark](https://mlsanity.com/paper/2311.06750/) (2023)
- [Visual Representation Learning Does Not Generalize Strongly Within the Same Domain](https://mlsanity.com/paper/2107.08221/) (2021)
- [Assaying Out-Of-Distribution Generalization in Transfer Learning](https://mlsanity.com/paper/2207.09239/) (2022)
- [Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization](https://mlsanity.com/paper/2106.06916/) (2021)
- [Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration](https://mlsanity.com/paper/2107.05446/) (2021)
- [Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning](https://mlsanity.com/paper/2309.16286/) (2023)
- [Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity](https://mlsanity.com/paper/2405.16585/) (2024)
- [Integrative conformal p-values for powerful out-of-distribution testing with labeled outliers](https://mlsanity.com/paper/2208.11111/) (2022)
- [Joint Task and Data Oriented Semantic Communications: A Deep Separate Source-channel Coding Scheme](https://mlsanity.com/paper/2302.13580/) (2023)
- [Confidence-aware Personalized Federated Learning via Variational Expectation Maximization](https://mlsanity.com/paper/2305.12557/) (2023)
- [The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents](https://mlsanity.com/paper/2107.05686/) (2021)
- [Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learning](https://mlsanity.com/paper/2503.06457/) (2025)
- [DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices](https://mlsanity.com/paper/2412.05823/) (2024)
- [Handling Data Heterogeneity via Architectural Design for Federated Visual Recognition](https://mlsanity.com/paper/2310.15165/) (2023)
- [Toward Robust Non-Transferable Learning: A Survey and Benchmark](https://mlsanity.com/paper/2502.13593/) (2025)
- [AQuA: Analytical Quality Assessment for Optimizing Video Analytics Systems](https://mlsanity.com/paper/2101.09752/) (2021)
- [When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need](https://mlsanity.com/paper/2507.04119/) (2025)
- [W2WNet: a two-module probabilistic Convolutional Neural Network with embedded data cleansing functionality](https://mlsanity.com/paper/2103.13107/) (2021)
- [Learning Fuzzy Clustering for SPECT/CT Segmentation via Convolutional Neural Networks](https://mlsanity.com/paper/2104.08623/) (2021)
- [Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks](https://mlsanity.com/paper/2106.00673/) (2021)
- [Geometric feature performance under downsampling for EEG classification tasks](https://mlsanity.com/paper/2102.07669/) (2021)
- [A Novel lightweight Convolutional Neural Network, ExquisiteNetV2](https://mlsanity.com/paper/2105.09008/) (2021)
- [Impact of Video Compression on the Performance of Object Detection Systems for Surveillance Applications](https://mlsanity.com/paper/2211.05805/) (2022)
- [Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenes](https://mlsanity.com/paper/2310.00558/) (2023)
- [Towards Federated Domain Unlearning: Verification Methodologies and Challenges](https://mlsanity.com/paper/2406.03078/) (2024)
- [Learning degraded image classification with restoration data fidelity](https://mlsanity.com/paper/2101.09606/) (2021)
- [What's color got to do with it? Face recognition in grayscale](https://mlsanity.com/paper/2309.05180/) (2023)
- [Pre-Trained Model Recommendation for Downstream Fine-tuning](https://mlsanity.com/paper/2403.06382/) (2024)

## 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.