YOLO-NAS-Bench samples 1500 YOLO architectures trained on COCO-mini, trains a LightGBM surrogate with self-evolving selection to reach R2 of 0.815, and uses it to evolve architectures outperforming official YOLOv8-12 baselines at similar latency.
NGBoost: Natural gradient boosting for probabilistic prediction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
YOLO-NAS-Bench: A Surrogate Benchmark with Self-Evolving Predictors for YOLO Architecture Search
YOLO-NAS-Bench samples 1500 YOLO architectures trained on COCO-mini, trains a LightGBM surrogate with self-evolving selection to reach R2 of 0.815, and uses it to evolve architectures outperforming official YOLOv8-12 baselines at similar latency.