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 reliability diagrams and ECE / class-wise ECE reports.
- Provides calibration utilities used by the imagery-aware contrastive MT evaluation code.
Supports:
Assessing the Role of Imagery in Multimodal Machine Translation
Companion code for OpenStreetMap-guided temporal satellite imagery collection and annotation.
- Generate OpenStreetMap-guided download manifests for temporal imagery.
- Label construction phases with the bundled annotation app.
- Export train/val/test splits for change-detection baselines.
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.
- Tune per-class thresholds on ImageNet, iNaturalist, or custom datasets.
- Export coverage/accuracy curves and selective-accuracy plots.
- Apply learned reject thresholds to existing PyTorch classifier outputs.
Supports:
Learning When to Say "I Don't Know" , Naturally Constrained Reject Option Classification