Research code and datasets.

2.1

osu-cvl/calibration

PyTorch calibration utilities for histogram binning, global temperature scaling, and class-wise temperature scaling.

• Python
• PyTorch
• calibration

1. Run global and class-wise temperature scaling on classifier logits.
2. Produce the calibration plots and expected-calibration-error summaries implemented in the repository.
3. Use the utilities as building blocks for calibration experiments.

2.2

osu-cvl/learning-idk

Companion code for ISVC 2022 / MVA 2025: per-class reject-option classification with binomial threshold search.

• Python
• PyTorch
• selective prediction

1. Learn per-class reject thresholds from precomputed classifier logits and labels.
2. Evaluate select accuracy, reject accuracy, and coverage for the learned thresholds.
3. 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

2.3

osu-cvl/Construction-Site-Satellite-Imagery-Collection

Companion code for OpenStreetMap-guided temporal satellite imagery collection and annotation.

• Python
• OpenStreetMap
• remote sensing

1. Extract candidate construction-site polygons from OpenStreetMap data.
2. Download temporal satellite imagery for the extracted regions.
3. 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