Deep Ordinal Regression with Label Diversity

29 Jun 2020  ·  Axel Berg, Magnus Oskarsson, Mark 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. However, it is not clear how the set of discrete classes should be chosen and how it affects the overall solution. In this work, we propose that using several discrete data representations simultaneously can improve neural network learning compared to a single representation. Our approach is end-to-end differentiable and can be added as a simple extension to conventional learning methods, such as deep neural networks. We test our method on three challenging tasks and show that our method reduces the prediction error compared to a baseline RvC approach while maintaining a similar model complexity.

PDF Abstract

Datasets


Results from the Paper


Ranked #2 on Head Pose Estimation on BIWI (MAE (trained with BIWI data) metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Head Pose Estimation BIWI Direct Regression MAE (trained with BIWI data) 2.54 # 2
Historical Color Image Dating HCI Label Diversity MAE 0.67 # 2
Age Estimation UTKFace Randomized Bins MAE 4.55 # 12

Methods


No methods listed for this paper. Add relevant methods here