Photofeeler-D3: A Neural Network with Voter Modeling for Dating Photo Impression Prediction
This addresses the need for accurate and adaptable AI tools to help young people select better dating photos, improving their chances of forming romantic connections online.
The paper tackled the problem of predicting impressions from dating profile photos, which is crucial for online dating, by introducing Photofeeler-D3, a convolutional neural network that achieves accuracy comparable to 10 human votes for smart, trustworthy, and attractive ratings, and sets state-of-the-art results in both Dating Photo Impression Prediction and Facial Beauty Prediction.
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.