EUVIMEDSkopri EUVIMED
Open access · CC BY 4.0

Explanation Retention Under Quantization and Temporal Reuse in Real-Time Object Detection: A YOLOv10x Study on Edge Platforms

Surbhi Bahri, Hussein T. Mouftah

Electronics · 2026-11-20 · 15 (22) · 5420

DOI: 10.3390/electronics15225420 ↗

At a glance

Journal article in Electronics, published online on 2026-11-20. Written by Surbhi Bahri and 1 co-authors. The full text is freely available (open access, CC BY 4.0).

AstrattDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Explanations released by a real-time object detector are often validated at full precision and assumed to remain stable after edge quantization. We test this assumption for a frozen YOLOv10x detector with a fused Grad-CAM teacher and a distilled forward-only surrogate under FP16 and INT8 deployment in five regimes from BDD100K and VisDrone-VID2019. Detection retention is measured by relative mAP and explanation retention by agreement between deployed and full-precision surrogate maps. Under INT8, explanation agreement fell by 5.8–11.4%, 5.4–7.3 times the noise floor of a 1/255 input perturbation, while mAP fell by 1.7–7.1%; on pairs not used to develop the surrogate, the loss was 9.6%. Controls attributed about three quarters of the loss to the feature-change step of a fixed-box-first decomposition, and showed that the asymmetry persisted on training-excluded sequences and across training seeds and calibration sets and that the surrogate’s maps depend on the learned weights. Two regimes repeated on a Jetson AGX Orin gave similar results. A motion-aware transport operator gave model-estimated reuse ages from 26 frames in daylight to six in dense traffic. Accuracy alone therefore does not establish that a detector’s explanations are retained after deployment.

Cite

APA

Bahri, S., & Mouftah, H. T. (2026). Explanation Retention Under Quantization and Temporal Reuse in Real-Time Object Detection: A YOLOv10x Study on Edge Platforms. Electronics, 15(22), 5420. https://doi.org/10.3390/electronics15225420

Vancouver

Bahri S, Mouftah HT. Explanation Retention Under Quantization and Temporal Reuse in Real-Time Object Detection: A YOLOv10x Study on Edge Platforms. Electronics. 2026;15(22):5420. doi:10.3390/electronics15225420

BibTeX
@article{Bahri2026,
  author = {Bahri, Surbhi and Mouftah, Hussein T.},
  title = {Explanation Retention Under Quantization and Temporal Reuse in Real-Time Object Detection: A YOLOv10x Study on Edge Platforms},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {22},
  pages = {5420},
  doi = {10.3390/electronics15225420}
}
Start for free →