# Confidence-Controlled XAI Auditing for Pedestrian Detection under Domain Shift

arXiv: https://arxiv.org/abs/2610.02364 · HTML: https://mlsanity.com/paper/2610.02364/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Builds on (most cited first, 9 of 9)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [Eigen-CAM: Class Activation Map using Principal Components](https://mlsanity.com/paper/2008.00299/) (2020)
- [CityPersons: A Diverse Dataset for Pedestrian Detection](https://mlsanity.com/paper/1702.05693/) (2017)
- [Explanations in Autonomous Driving: A Survey](https://mlsanity.com/paper/2103.05154/) (2021)
- [Black-box Explanation of Object Detectors via Saliency Maps](https://mlsanity.com/paper/2006.03204/) (2020)
- [On the Black-box Explainability of Object Detection Models for Safe and Trustworthy Industrial Applications](https://mlsanity.com/paper/2411.00818/) (2024)

## Abstract (arXiv)

Explainability is increasingly required for perception models in intelligent vehicles, yet whether explanations remain faithful under driving domain shift is still poorly understood. This work audits post-hoc explanations of a fixed YOLOv8s pedestrian detector across PIE and JAAD using ROI-based D-Deletion, frozen confidence terciles, rank-based tests, bootstrap intervals, and Holm correction. The audit shows that deletion-based faithfulness is strongly coupled to detection strength at explanation time, with Spearman correlations between 0.70 and 0.82 for D-RISE, making naive confidence-stratified comparisons unreliable. After controlling for detection strength within fixed f0 bins, D-RISE faithfulness remains domain-dependent in the central f0 range, with PIE showing higher D-Deletion than JAAD and Holm-adjusted significance. A non-perturbative EigenCAM baseline is less faithful than D-RISE but also exhibits score coupling, suggesting that the effect is not specific to D-RISE and is related to the deletion-based evaluation setup. These results motivate confidence-controlled XAI audits for safety-critical perception under domain shift.