Deep Ordinal Regression with Label Diversity

29 Jun 2020Axel BergMagnus OskarssonMark O'Connor

Regression via classification (RvC) is a common method used for regression problems in deep learning, where the target variable belongs to a set of continuous values. By discretizing the target into a set of non-overlapping classes, it has been shown that training a classifier can improve neural network accuracy compared to using a standard regression approach... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Head Pose Estimation BIWI Direct Regression MAE 2.54 # 1
Historical Color Image Dating HCI Label Diversity MAE 0.67 # 2
Age Estimation UTKFace Randomized Bins MAE 4.55 # 1