DEX: Deep EXpectation of Apparent Age from a Single Image

By Rasmus Rothe, Radu Timofte, Luc Van Gool. 2015

749 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Dermatology

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Dermatology

Citations in the corpus

Diversity in Faces (2019, methodology): “In order to predict age using DEX, each face was pre-processed as in [74].”
Compacting, Picking and Growing for Unforgetting Continual Learning (2019, methodology): “For gender classification, we combine FotW [9] and IMDB-Wiki [37] datasets and classify faces into three categories, male, female and other.”
Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings (2018, methodology): “As stated by the authors, however, these images often contain other actors, who co-starred in their movies [19].”
AgeDB: The First Manually Collected, In-the-Wild Age Database (2017, methodology): “For the AgeDB “in-the-wild” database, the MAE for the pre-trained DEX deep network [39] is 13.”
Incorporating Side Information by Adaptive Convolution (2017, methodology): “…task is used as our auxiliary task because, empirically, classiﬁcation is more robust to train than regression since it only needs to decide to which class the input belongs (i.e., form partitions of the feature space), rather than predicts an exact real number (Niu et al. 2016; Rothe et al. 2015).”
ChaLearn Looking at People and Faces of the World: Face AnalysisWorkshop and Challenge 2016 (2016, methodology): “They fine-tune this CNN on the IMDB-Wiki dataset [40] for the age estimation task using the label distribution encoding [20].”
LARGE: Latent-Based Regression through GAN Semantics (2021, methodology): “When ground truths are not available, we either annotate existing datasets using pretrained networks (WHENet [77] and DEX [47]) or evaluate our performance by considering relative ordering of image collections.”
Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation (2020, methodology): “To test BERT-Classification on dialog pairs, we apply the DEX trick (Rothe et al., 2015) to get”
Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments (2017, methodology): “To estimate the age of each image, we use Dex [14] which is the winner of the ChaLearn LAP 2015 challenge on age estimation and the name of each image is formed as follows: We then form training and testing sets.”
Third Time's the Charm? Image and Video Editing with StyleGAN3 (2022, methodology): “[57,58] for age, and the classiﬁer from Lin et al .”
Toward Interpretable Machine Learning: Transparent Deep Neural Networks and Beyond (2020, methodology): “One reason the model has learned that connection in the ﬁrst place is the extreme population imbalance among the age groups of the Adience dataset; a problem which is shared with many other datasets of face images, e.g. [61], [120].”
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications (2021, methodology): “The IMDB-WIKI dataset consists of 523,051 images from 20,284 celebrities (460,723 images from the Internet Movie Data Base (Imdb) and 62,328 images from Wikipedia) at different ages, labelled with 101 labels (0-100 years, one label per year).”