Boxes2Pixels distills noisy SAM pseudo-masks into a compact DINOv2-based student with auxiliary localization and one-sided self-correction, delivering +6.97 anomaly mIoU and +9.71 binary IoU gains over baselines on wind turbine data with 80% fewer parameters.
What uncertainties do we need in bayesian deep learning for computer vision?Advances in neural information processing systems, 30
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Consensus Entropy measures inter-VLM output agreement to verify OCR reliability and enable self-improving ensembles, yielding 42.1% F1 gains over single-model judging.
Optimal allocation screens units at the margin of algorithmic decisions and directly targets highest-risk units, with screening efficiency gains increasing as aleatoric uncertainty rises.
citing papers explorer
-
Boxes2Pixels: Learning Defect Segmentation from Noisy SAM Masks
Boxes2Pixels distills noisy SAM pseudo-masks into a compact DINOv2-based student with auxiliary localization and one-sided self-correction, delivering +6.97 anomaly mIoU and +9.71 binary IoU gains over baselines on wind turbine data with 80% fewer parameters.
-
Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR
Consensus Entropy measures inter-VLM output agreement to verify OCR reliability and enable self-improving ensembles, yielding 42.1% F1 gains over single-model judging.
-
The Limits of AI-Driven Allocation: Optimal Screening under Aleatoric Uncertainty
Optimal allocation screens units at the margin of algorithmic decisions and directly targets highest-risk units, with screening efficiency gains increasing as aleatoric uncertainty rises.