Abstract
Clinical vision models are often deployed as frozen black boxes with no access to internals, retraining, or ground truth at inference time. We introduce \textbf{SpatialUQ}, a post-hoc uncertainty method using only output probabilities. It measures the Jensen-Shannon divergence between the global prediction and the mean of five fixed spatial crops in six deterministic forward passes. The premise is simple, trustworthy predictions are spatially consistent. On NIH ChestX-ray14 (DenseNet-121, $N{=}25{,}596$), our Multicrop Uncertainty Score (MUS) reaches $0.784$ failure-detection AUC versus $0.664$ for MC-Dropout ($p{<}10^{-6}$) at one-fifth the compute, with native calibration ($\text{SCE}{=}0.049$ vs.\ $0.127$ for $\ell_1$), the best-calibrated among methods above 0.78 AUC. A supervised fusion of MUS with entropy, confidence, and $\ell_1$ reaches $0.832$, outperforming a five-member ensemble ($0.813$). MUS scales with model quality, reaching $0.899$ with BiomedCLIP ($ρ= 0.846$), while this relationship remains meaningful in-distribution ($ρ= 0.523$) but breaks down under severe distribution shift (VinBigData, $ρ= 0.027$). MUS is well-suited to diffuse findings but is less dependable for small focal lesions such as nodules. Code and experimental materials are publicly available at https://huggingface.co/datasets/kawsher11/SpatialUQ.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Mahbub, M. K., Biswas, M., Morshed, M. N., & Yu, W. (2026). SpatialUQ: Post-Hoc Uncertainty Quantification from Spatial Consistency in Black-Box Vision Models. https://omanscience.com/en/articles/spatialuq-post-hoc-uncertainty-quantification-from-spatial-consistency-in-black-box-vision-models
MLA 9
Mahbub, Md Kawsher, et al. "SpatialUQ: Post-Hoc Uncertainty Quantification from Spatial Consistency in Black-Box Vision Models." https://omanscience.com/en/articles/spatialuq-post-hoc-uncertainty-quantification-from-spatial-consistency-in-black-box-vision-models.
Chicago (author–date)
Mahbub, Md Kawsher, Milon Biswas, Mirza Niaz Morshed, and Wei Yu. 2026. "SpatialUQ: Post-Hoc Uncertainty Quantification from Spatial Consistency in Black-Box Vision Models." https://omanscience.com/en/articles/spatialuq-post-hoc-uncertainty-quantification-from-spatial-consistency-in-black-box-vision-models.
Harvard
Mahbub, M. K., Biswas, M., Morshed, M. N. and Yu, W. (2026) 'SpatialUQ: Post-Hoc Uncertainty Quantification from Spatial Consistency in Black-Box Vision Models', Available at: https://omanscience.com/en/articles/spatialuq-post-hoc-uncertainty-quantification-from-spatial-consistency-in-black-box-vision-models.
Vancouver
Mahbub MK, Biswas M, Morshed MN, Yu W. SpatialUQ: Post-Hoc Uncertainty Quantification from Spatial Consistency in Black-Box Vision Models. https://omanscience.com/en/articles/spatialuq-post-hoc-uncertainty-quantification-from-spatial-consistency-in-black-box-vision-models
IEEE
M. K. Mahbub, M. Biswas, M. N. Morshed, and W. Yu, "SpatialUQ: Post-Hoc Uncertainty Quantification from Spatial Consistency in Black-Box Vision Models," https://omanscience.com/en/articles/spatialuq-post-hoc-uncertainty-quantification-from-spatial-consistency-in-black-box-vision-models.