# Image Quality Dependent Degradation for AI Systems

arXiv: https://arxiv.org/abs/2607.25736 · HTML: https://mlsanity.com/paper/2607.25736/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [A Survey of Autonomous Driving: Common Practices and Emerging Technologies](https://mlsanity.com/paper/1906.05113/) (2019)
- [Why Normalizing Flows Fail to Detect Out-of-Distribution Data](https://mlsanity.com/paper/2006.08545/) (2020)
- [RankIQA: Learning from Rankings for No-reference Image Quality Assessment](https://mlsanity.com/paper/1707.08347/) (2017)
- [A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement](https://mlsanity.com/paper/2204.09308/) (2022)
- [Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving](https://mlsanity.com/paper/2305.02008/) (2023)
- [Perception and Sensing for Autonomous Vehicles Under Adverse Weather Conditions: A Survey](https://mlsanity.com/paper/2112.08936/) (2021)
- [Emergent Visual Sensors for Autonomous Vehicles](https://mlsanity.com/paper/2205.09383/) (2022)
- [Worsening Perception: Real-time Degradation of Autonomous Vehicle Perception Performance for Simulation of Adverse Weather Conditions](https://mlsanity.com/paper/2103.02760/) (2021)
- [Learning Densities in Feature Space for Reliable Segmentation of Indoor Scenes](https://mlsanity.com/paper/1908.00448/) (2019)
- [Feature Density Estimation for Out-of-Distribution Detection via Normalizing Flows](https://mlsanity.com/paper/2402.06537/) (2024)
- [A Taxonomy to Unify Fault Tolerance Regimes for Automotive Systems: Defining Fail-Operational, Fail-Degraded, and Fail-Safe](https://mlsanity.com/paper/2106.11042/) (2021)
- [Toward Robust LiDAR based 3D Object Detection via Density-Aware Adaptive Thresholding](https://mlsanity.com/paper/2404.13852/) (2024)
- [Formal Verification of a Fail-Operational Automotive Driving System](https://mlsanity.com/paper/2101.07307/) (2021)
- [Reliability Analysis of Gracefully Degrading Automotive Systems](https://mlsanity.com/paper/2305.07401/) (2023)
- [Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection](https://mlsanity.com/paper/2511.10308/) (2025)
- [The Role of Noisy Data in Improving CNN Robustness for Image Classification](https://mlsanity.com/paper/2601.08043/) (2026)

## Abstract (arXiv)

Perception is one of the primary applications where neural networks outperform conventional algorithms. One example is AI systems for automated driving, which can detect pedestrians based on image data and avoid them accordingly. A substantial challenge with these AI systems is that their output depends heavily on the quality of the input images. For example, if an image is of inferior quality due to heavy contamination, such as noise or darkness, accurate predictions are hardly feasible. Additionally, various types of errors can occur, each with varying relevance to the trustworthiness of the underlying AI system. In particular, it may be more critical not to detect an existing person than to detect a person where there is none. Therefore, we want to show that we can still avoid the most critical errors in situations of inferior image quality. To achieve this, we aim to establish a fail-degraded system by lowering the network's confidence threshold based on the estimated image quality, enabling it to detect objects more cautiously in uncertain situations. Additionally, we present a novel method for estimating the quality of incoming images by comparing them to the training data using normalizing flows. We will also conduct experiments applying our method to state-of-the-art object detection. In summary, we will present a design strategy for AI-based systems in automated driving that can deal with poor-quality input data without resorting to fallback solutions. Such measures enhance trust in AI-based systems and lead to an increased provision of the AI component.