Hidden

EELS — Hidden Tier

(3 scenes)

Fully blind server-side evaluation — no data download.

What you get

No data downloadable. Algorithm runs server-side on hidden measurements.

How to use

Package algorithm as Docker container / Python script. Submit via link.

What to submit

Containerized algorithm accepting y + H, outputting x_hat + corrected spec.

Parameter Specifications

🔒

True spec hidden — blind evaluation, only ranges available.

Parameter Spec Range Unit
energy_dispersion -0.0014 – 0.0046 eV/channel
zero_loss_shift -0.21 – 0.69 eV
aberration -1.4 – 4.6 %

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SwinEELS + gradient 0.745 31.06 0.932 0.81 ✓ Certified Wang et al., npj Comput. Mater. 2023
2 PhysEELS + gradient 0.722 28.85 0.898 0.87 ✓ Certified Chen et al., Microsc. Microanal. 2024
3 TransEELS + gradient 0.694 28.56 0.892 0.76 ✓ Certified Li et al., Ultramicroscopy 2022
4 DiffEELS + gradient 0.654 26.34 0.841 0.77 ✓ Certified Gao et al., NeurIPS 2024
5 N2V-EELS + gradient 0.563 22.1 0.694 0.82 ✓ Certified Krull et al., NeurIPS 2019
6 PowerLaw-EELS + gradient 0.474 18.73 0.536 0.86 ✓ Certified Egerton, EELS in the EM, Springer 2011
7 DnCNN-EELS + gradient 0.448 18.4 0.52 0.78 ✓ Certified Kovarik et al., npj Comput. Mater. 2016
8 MLS-EELS + gradient 0.372 16.0 0.401 0.76 ✓ Certified Verbeeck & Van Aert, Ultramicroscopy 2004
9 ICA-EELS + gradient 0.310 13.77 0.3 0.76 ✓ Certified Bosman et al., Ultramicroscopy 2006

Dataset

Scenes: 3

Scoring Formula

0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

PSNR: 40% SSIM: 40% Consistency: 20%
Back to EELS