Beyond Wisdom of Crowds: Deep Uncertainty Coding for Apparent Age Estimation
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Details
| Original language | English |
|---|---|
| Title of host publication | 2019 IEEE 4th International Conference on Image, Vision and Computing (ICIVC) |
| Publisher | IEEE |
| Pages | 658-662 |
| Number of pages | 5 |
| ISBN (Electronic) | 978-1-7281-2325-7 |
| ISBN (Print) | 978-1-7281-2326-4 |
| DOIs | |
| Publication status | Published - 2019 |
| Publication type | A4 Article in a conference publication |
| Event | International Conference on Image, Vision and Computing - Duration: 1 Jan 2000 → … |
Conference
| Conference | International Conference on Image, Vision and Computing |
|---|---|
| Period | 1/01/00 → … |
Abstract
Conventional algorithms for apparent age estimation make a strong assumption that the wisdom of crowds (i.e. the mean value of inconsistently annotated age labels) is superior to any individual. In this paper, we go beyond such an assumption and instead of averaging to remove label uncertainty we cope with label uncertainty in training by introducing a new concept of uncertainty coding. Uncertainty coding encodes multiple unary apparent age labels into a binary vector indicating age range (uncertainty) in the target space. We traverse through convolutional features and architecture to learn deep uncertainty mapping, whose predicted codes as mid-level features are fed into the second layer regressor that outputs a target prediction. We conduct experiments on the ChaLearn and FG-NET benchmarks to demonstrate superior performance of the proposed deep uncertainty coding to the state-of-the-arts.