# Facial age estimation by deep residual decision making

Source: [Facial age estimation by deep residual decision making](<https://www.sota2.com/research/paper/68fa66461e209131cea0f67d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T04:08:19.277Z

Authors: Shichao Li, Kwang-Ting Cheng

Published: 2019-08-28T14:12:04.000Z

## Abstract

Residual representation learning simplifies the optimization problem of learning complex functions and has been widely used by traditional convolutional neural networks. However, it has not been applied to deep neural decision forest (NDF). In this paper we incorporate residual learning into NDF and the resulting model achieves state-of-the-art level accuracy on three public age estimation benchmarks while requiring less memory and computation. We further employ gradient-based technique to visualize the decision-making process of NDF and understand how it is influenced by facial image inputs. The code and pre-trained models will be available at https://github.com/Nicholasli1995/VisualizingNDF.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Facial Age Estimation on CACD (test)](<https://www.sota2.com/research/sota/facial-age-estimation-on-cacd-test.md>): Facial Age Estimation; CACD (test); MAE: 4.595.

- [Facial Age Estimation on FG-NET (leave-one-out cross validation)](<https://www.sota2.com/research/sota/facial-age-estimation-on-fg-net-leave-one-out-cross-validation.md>): Facial Age Estimation; FG-NET (leave-one-out cross validation); MAE: 3.87.

- [Facial Age Estimation on MORPH (80-20 train test)](<https://www.sota2.com/research/sota/facial-age-estimation-on-morph-80-20-train-test.md>): Facial Age Estimation; MORPH (80-20 train test); MAE: 2.97.

- [Age estimation on CACD (RS (Random Split))](<https://www.sota2.com/research/sota/age-estimation-on-cacd-rs-random-split.md>): Age Estimation; CACD (RS (Random Split)); MAE: 4.6.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1908.10737>)

[PDF](<https://arxiv.org/pdf/1908.10737.pdf>)

[Implementation](<https://github.com/Nicholasli1995/VisualizingNDF>)
