SpatialUQ: Post-Hoc Uncertainty Quantification from Spatial Consistency in Black-Box Vision Models
Read the original on arXiv Machine Learning →SpatialUQ is a post‑hoc uncertainty quantification method that uses only the output probabilities of frozen black‑box vision models. It computes the Jensen‑Shannon divergence between the global prediction and the mean of five fixed spatial crops across six deterministic forward passes, assuming that trustworthy predictions are spatially consistent. On the NIH ChestX‑ray14 dataset, SpatialUQ’s Multicrop Uncertainty Score (MUS) achieves a 0.784 failure‑detection AUC—significantly higher than MC‑Dropout—while also providing superior native calibration and improving further when fused with other uncertainty signals.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.