# Strengths and Weaknesses of Deep Learning Models for Face Recognition Against Image Degradations

arXiv: https://arxiv.org/abs/1710.01494 · HTML: https://mlsanity.com/paper/1710.01494/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2017.

## Built on by (most cited first, 19 of 19)

- [Towards Semantic Communications: Deep Learning-Based Image Semantic Coding](https://mlsanity.com/paper/2208.04094/) (2022)
- [Face Recognition Accuracy Across Demographics: Shining a Light Into the Problem](https://mlsanity.com/paper/2206.01881/) (2022)
- [DifFIQA: Face Image Quality Assessment Using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2305.05768/) (2023)
- [FaceQAN: Face Image Quality Assessment Through Adversarial Noise Exploration](https://mlsanity.com/paper/2212.02127/) (2022)
- [On Recognizing Occluded Faces in the Wild](https://mlsanity.com/paper/2109.03672/) (2021)
- [Face Morphing Attack Detection with Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2306.15733/) (2023)
- [Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models](https://mlsanity.com/paper/2108.06581/) (2021)
- [Fair SA: Sensitivity Analysis for Fairness in Face Recognition](https://mlsanity.com/paper/2202.03586/) (2022)
- [Face Morphing Attack Detection Using Privacy-Aware Training Data](https://mlsanity.com/paper/2207.00899/) (2022)
- [SelfMAD: Enhancing Generalization and Robustness in Morphing Attack Detection via Self-Supervised Learning](https://mlsanity.com/paper/2504.05504/) (2025)
- [Assessing Bias in Face Image Quality Assessment](https://mlsanity.com/paper/2211.15265/) (2022)
- [Assessment Framework for Deepfake Detection in Real-world Situations](https://mlsanity.com/paper/2304.06125/) (2023)
- [FROQ: Observing Face Recognition Models for Efficient Quality Assessment](https://mlsanity.com/paper/2509.17689/) (2025)
- [Incremental cluster validity index-guided online learning for performance and robustness to presentation order](https://mlsanity.com/paper/2108.07743/) (2021)
- [Performance Evaluation of Action Recognition Models on Low Quality Videos](https://mlsanity.com/paper/2204.09166/) (2022)
- [Cross-resolution Face Recognition via Identity-Preserving Network and Knowledge Distillation](https://mlsanity.com/paper/2303.08665/) (2023)
- [Analyzing the Effect of Combined Degradations on Face Recognition](https://mlsanity.com/paper/2406.02142/) (2024)
- [What's color got to do with it? Face recognition in grayscale](https://mlsanity.com/paper/2309.05180/) (2023)
- [SNAP: A Benchmark for Testing the Effects of Capture Conditions on Fundamental Vision Tasks](https://mlsanity.com/paper/2505.15628/) (2025)

## Abstract (arXiv)

Deep convolutional neural networks (CNNs) based approaches are the state-of-the-art in various computer vision tasks, including face recognition. Considerable research effort is currently being directed towards further improving deep CNNs by focusing on more powerful model architectures and better learning techniques. However, studies systematically exploring the strengths and weaknesses of existing deep models for face recognition are still relatively scarce in the literature. In this paper, we try to fill this gap and study the effects of different covariates on the verification performance of four recent deep CNN models using the Labeled Faces in the Wild (LFW) dataset. Specifically, we investigate the influence of covariates related to: image quality -- blur, JPEG compression, occlusion, noise, image brightness, contrast, missing pixels; and model characteristics -- CNN architecture, color information, descriptor computation; and analyze their impact on the face verification performance of AlexNet, VGG-Face, GoogLeNet, and SqueezeNet. Based on comprehensive and rigorous experimentation, we identify the strengths and weaknesses of the deep learning models, and present key areas for potential future research. Our results indicate that high levels of noise, blur, missing pixels, and brightness have a detrimental effect on the verification performance of all models, whereas the impact of contrast changes and compression artifacts is limited. It has been found that the descriptor computation strategy and color information does not have a significant influence on performance.