PyTorch calibration utilities for histogram binning, global temperature scaling, and class-wise temperature scaling.
- Run global and class-wise temperature scaling on classifier logits.
- Produce the calibration plots and expected-calibration-error summaries implemented in the repository.
- Use the utilities as building blocks; this repository is not the WMT evaluation harness.
Supports:
Assessing the Role of Imagery in Multimodal Machine Translation
Companion code for OpenStreetMap-guided temporal satellite imagery collection and annotation.
- Extract candidate construction-site polygons from OpenStreetMap data.
- Download temporal satellite imagery for the extracted regions.
- Inspect the released sample dataset and notebook; annotation and split-export tools are not included.
Supports:
A Framework for Semi-automatic Collection of Temporal Satellite Imagery for Analysis of Dynamic Regions
Companion code for ISVC 2022 / MVA 2025: per-class reject-option classification with binomial threshold search.
- Learn per-class reject thresholds from precomputed classifier logits and labels.
- Evaluate select accuracy, reject accuracy, and coverage for the learned thresholds.
- Run the included calibration and threshold-analysis utilities; no coverage-curve exporter is bundled.
Supports:
Learning When to Say "I Don't Know" , Naturally Constrained Reject Option Classification