Photofeeler-D3: A Neural Network with Voter Modeling for Dating Photo Impression Prediction

Abstract

In just a few years, online dating has become the dominant way that young people meet to date, making the deceptively error-prone task of picking good dating profile photos vital to a generation's ability to form romantic connections. Until now, artificial intelligence approaches to Dating Photo Impression Prediction (DPIP) have been very inaccurate, unadaptable to real-world application, and have only taken into account a subject's physical attractiveness. To that effect, we propose Photofeeler-D3 -the first convolutional neural network as accurate as 10 human votes for how smart, trustworthy, and attractive the subject appears in highly variable dating photos. Our "attractive" output is also applicable to Facial Beauty Prediction (FBP), making Photofeeler-D3 state-of-the-art for both DPIP and FBP. We achieve this by leveraging Photofeeler's Dating Dataset (PDD) with over 1 million images and tens of millions of votes, our novel technique of voter modeling, and cutting-edge computer vision techniques.

Multi-concept adversarial attacks

“…For example, an ML model may be trained to predict privacy-sensitive information such as sexual orientation and/or political affiliation using social network profiles [11,21,27]. Recent work has shown similar intrusive usages of ML models, predicting attractiveness using profile pictures [9,13], and reporting life satisfaction [1,22]. Although some of these usages seem innocuous, the deployment of such ML models may be seen as a threat to individual privacy.…”