arXiv cs.AI· Guangtao Zhang, Haonan Wu, Junxuan Gao, Zhengyang Liu, Zhaoxi Zeng, Zhihao Li, Jianguo Huang, Zhiqiang Liu·· 12 小时前AI 评分26
CARM：面向可靠科学超分辨率的共形自适应风险掩码
CARM: Conformal Adaptive Risk Masking for Reliable Scientific Super-Resolution
AI 导读
CARM 是一个在时序分布偏移下自适应控制空间风险的统计框架，通过维护不同更新速率的专家并用非对称代理损失在线聚合阈值，可与任意提供空间不确定性分数的超分辨率模型配合使用。
正文 · 原文
Abstract:Deep learning-based super-resolution (SR) can reconstruct fine-scale Earth-observation fields from coarse observations, but reconstruction accuracy alone does not provide a calibrated rule for identifying reliable spatial regions. Conformal Mask Calibration (CMC), built on conformal risk control, converts a spatial uncertainty score into a trust mask and controls the expected worst-case local distortion under exchangeability. However, its fixed threshold can become miscalibrated in Earth-observation streams affected by seasonality and episodic events. We propose $\textit{CARM}$ (Conformal Adaptive Risk Masking), a statistical framework for adaptive spatial risk control under temporal distribution shift. CARM maintains experts with heterogeneous update rates and aggregates their threshold proposals online using an asymmetric surrogate loss, balancing rapid adaptation to distribution changes against stability during relatively stationary periods. All updates are causal and use only mature feedback available after a fixed delay, allowing CARM to operate with any SR model that provides a spatial uncertainty score. We prove that the time-averaged mask-conditioned risk converges to at most $\alpha$ at an $O(1/T)$ rate, without distributional assumptions and for any choice of aggregation weights across experts. On a daily South China Sea chlorophyll-$\textit{a}$ SR stream, CARM reduces the empirical violation rate from $43.49\%$ to $9.38\%$ and the moving-average exceedance frequency from $47.29\%$ to $1.22\%$ at $\alpha=0.10$, while retaining a non-trivial trusted region. Experiments on ERA5 wind and OSTIA sea-surface temperature further show consistent relative improvements across multiple SR backbones.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Probability (math.PR) |
| Cite as: | arXiv:2611.06151 [cs.AI] |
| (or arXiv:2611.06151v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06151 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jianguo Huang [view email]
[v1]
Wed, 4 Nov 2026 08:32:19 UTC (389 KB)
来源：arXiv cs.AI · arxiv.org