Understanding and Comparing Deep Neural Networks for Age and Gender Classification

By Wojciech Samek, Alexander Binder, Sebastian Lapuschkin, K. Müller. 2017

143 citations recorded by the source corpus.

Recently, deep neural networks have demonstrated excellent performances in recognizing the age and gender on human face images. However, these models were applied in a black-box manner with no information provided about which facial features are actually used for prediction and how these features depend on image preprocessing, model initialization and architecture choice. We present a study investigating these different effects. In detail, our work compares four popular neural network architectures, studies the effect of pretraining, evaluates the robustness of the considered alignment preprocessings via cross-method test set swapping and intuitively visualizes the model's prediction strategies in given preprocessing conditions using the recent Layer-wise Relevance Propagation (LRP) algorithm. Our evaluations on the challenging Adience benchmark show that suitable parameter initialization leads to a holistic perception of the input, compensating artefactual data representations. With a combination of simple preprocessing steps, we reach state of the art performance in gender recognition.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Unmasking Clever Hans predictors and assessing what machines really learn (2019, methodology): “Explanation methods were successfully applied to a wide set of complex real-world problems such as the analysis of faces [81, 123, 124], EEG and fMRI data [23, 50], human gait [48], videos [125], speech [126], reinforcement learning [25], biological data [127], text [26,128,129], or comparing human ”
Explaining the unique nature of individual gait patterns with deep learning (2018, methodology): “Similar results have been found on photographic image data [3, 37].”
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications (2021, methodology): “Specifically, we will now try an alternate LRP preset called ‘LRP-CMP’ that applies a composite strategy [103], [126], [94] where different rules are applied at different layers.”
Explainable AI Methods - A Brief Overview (2020, background): “, computer vision [46], natural language processing [7], EEG analysis [78], meteorology [54], among others.”
Explaining and Interpreting LSTMs (2019, background): “On convolutional neural networks for computer vision, composite strategies making use of different rules at different layers have shown to work well in practice [43,51].”
Toward Interpretable Machine Learning: Transparent Deep Neural Networks and Beyond (2020, methodology): “Specifically, we will now try an alternate LRP preset called ‘LRP-CMP’ that applies a composite strategy [84], [98], [75] where different rules are applied at different layers.”
Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions (2023, background): “Explanations can also drive pruning and model compression strategies, linking irrelevant concepts to specific neurons that can hence be removed from a neural network [54].”