Confidence-Controlled XAI Auditing for Pedestrian Detection under Domain Shift

arXiv:2610.02364 · cs.CV · Submitted 2026-10-01 · Read on arXiv

cs.CV

Submitted: 2026-10-01

Updated: 2026-10-01

Comments: Accepted at the 2026 IEEE International Conference on Vehicular Electronics and Safety (ICVES 2026). 6 pages, 4 figures

Code: https://github.com/ultralytics/ultralytics

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Domain Shift — 1× in this paper · explained in 4 episodes

Sources

• RISE: Randomized Input Sampling for Explanation of Black-box Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models