The 2019 Challenge:

Explaining the Human Visual Brain

Track 2 (MEG) Challenge Test Set Leaderboard: Detailed Table

Back to simplified table

Early Interval Late Interval Score
Rank Team Name R2 Noise Normalized R2 (%) R2 Noise Normalized R2 (%) Average R2 Average Noise Normalized R2 (%)
Noise Ceiling 0.3562 100 0.4452 100 0.4007 100
1 Aakash 0.2100 58.9498 0.2994 67.2455 0.2547 63.5583
2 rmldj 0.1671 46.9061 0.2555 57.3847 0.2113 52.7272
3 agustin 0.1815 50.9508 0.2386 53.5932 0.2100 52.4187
4 ggaziv 0.1824 51.2056 0.1563 35.0976 0.1693 42.2571
5 Team GJ 0.1296 36.3899 0.2019 45.3534 0.1658 41.3694
6 drshti 0.0779 21.8638 0.1747 39.2335 0.1263 31.5132
7 mfonseca 0.0976 27.3910 0.1242 27.8964 0.1109 27.6718
8 Mukesh_Makwana 0.0739 20.7331 0.1187 26.6669 0.0963 24.0295
9 Team UvABrain 0.0043 1.1998 0.1269 28.5125 0.0656 16.3728
10 AlexNet-OrganizerBaseline 0.0207 5.8198 0.1021 22.9284 0.0614 15.3241
11 kpmtm 0.0924 25.9474 0.0196 4.4091 0.0560 13.9822
12 adrianso 0.0559 15.6797 0.0375 8.4270 0.0467 11.6506
13 am88 0.0221 6.1968 0.0642 14.4103 0.0431 10.7597
14 Wenxin_SU 0.0352 9.8936 0.0318 7.1345 0.0335 8.3608
15 jomaka 0.0011 0.3015 0.0380 8.5400 0.0195 4.8782
16 HY 0.0090 2.5384 0.0285 6.4005 0.0188 4.6839

The three main columns are Early and Late Interval (the two time intervals of interest), and Score (average of Early and Late). The entry with the highest Score is ranked first. R2 represents the submitted model RDM squared correlation (spearman) to the Early/Late Interval RDM. Noise Normalized R2 represents the fact that R2 values are normalized to the noise ceiling (see here for more details). AlexNet is the organizer baseline.