Benchmarks of YOLO models from nano to extra-large show that degradation-aware calibration for Static INT8 PTQ yields no broad robustness gains to input degradations over clean-data calibration, with limited exceptions for larger models under noise.
You Only Look Once: Unified, Real -Time Object Detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Quantization Robustness to Input Degradations for Object Detection
Benchmarks of YOLO models from nano to extra-large show that degradation-aware calibration for Static INT8 PTQ yields no broad robustness gains to input degradations over clean-data calibration, with limited exceptions for larger models under noise.