AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

LUMINA: A Multi-Vendor Mammography Benchmark with Energy Harmonization Protocol

Hongyi Pan, Gorkem Durak, Halil Ertugrul Aktas, Andrea M. Bejar, Baver Tutun, Emre Uysal, Ezgi Bulbul, Mehmet Fatih Dogan, Berrin Erok, Berna Akkus Yildirim, Sukru Mehmet Erturk, Ulas Bagci

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Confidence calibration objectives · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add foreground-only histogram harmonization (ablation)best two-view model · LUMINA diagnosis 224AUC (%): 91.42 -> 92.99Improved
add foreground-only histogram harmonization (ablation)best two-view model · LUMINA diagnosis 512AUC (%): 91.27 -> 93.54Improved
add foreground-only histogram harmonization (ablation)EfficientNet-B0 · LUMINA BI-RADS two-class 512AUC (%): 89.21 -> 92.75Improved
add foreground-only histogram harmonization (ablation)Swin-T · LUMINA density 512AUC (%): 88.92 -> 89.14No clear effect
use two views instead of single view (ablation)EfficientNet-B0 · LUMINA diagnosis 224AUC (%): 90.66 -> 92.99Improved
use two views instead of single view (ablation)DenseNet-121 · LUMINA diagnosis 512AUC (%): 90.52 -> 88.33Hurt
use two views instead of single view (ablation)ResNet-50 · LUMINA diagnosis 224AUC (%): 87.42 -> 88.71; accuracy 79.49 -> 76.70Mixed
raise input resolution from 224 to 512 (ablation)EfficientNet-B0 single-view · LUMINA diagnosisAUC (%): 90.66 -> 92.13Improved
raise input resolution from 224 to 512 (ablation)Swin-T · LUMINA densitymacro-AUC (%): 89.43 -> 89.14Hurt
share backbone between views instead of independent (ablation)EfficientNet-B0 two-view · LUMINA diagnosis 224AUC (%): 93.54 -> 92.99; params 8.34M -> 4.34MNo clear effect
share backbone between views instead of independent (ablation)EfficientNet-B0 two-view · LUMINA diagnosis 512AUC (%): 92.71 -> 93.54No clear effect
harmonize energy (ablation)models · LUMINA energy subsetsAUC (%): low-energy gain larger than high-energyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy