Challenges in Representation Learning: A report on three machine learning contests

1 Jul 2013Ian J. GoodfellowDumitru ErhanPierre Luc CarrierAaron CourvilleMehdi MirzaBen HamnerWill CukierskiYichuan TangDavid ThalerDong-Hyun LeeYingbo ZhouChetan RamaiahFangxiang FengRuifan LiXiaojie WangDimitris AthanasakisJohn Shawe-TaylorMaxim MilakovJohn ParkRadu IonescuMarius PopescuCristian GrozeaJames BergstraJingjing XieLukasz RomaszkoBing XuZhang ChuangYoshua Bengio

The ICML 2013 Workshop on Challenges in Representation Learning focused on three challenges: the black box learning challenge, the facial expression recognition challenge, and the multimodal learning challenge. We describe the datasets created for these challenges and summarize the results of the competitions... (read more)

PDF Abstract

Evaluation Results from the Paper


 SOTA for Facial Expression Recognition on FER2013 (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
COMPARE
Facial Expression Recognition FER2013 Residual Masking Network Accuracy 74.14 # 2
Facial Expression Recognition FER2013 Ensemble ResMaskingNet with 6 other CNNs Accuracy 76.82 # 1