Salienteye: Maximizing Engagement While Maintaining Artistic Style on Instagram Using Deep Neural Networks

TL;DR

This paper introduces Salienteye, a deep learning system that predicts Instagram photo engagement and assesses style similarity, helping photographers optimize their posts for maximum engagement while preserving their artistic style.

Contribution

It presents a novel approach combining transfer learning and style measurement models to personalize engagement and style predictions for Instagram photographers.

Findings

Models outperform baseline and human annotations

Effective personalization for individual Instagram accounts

Balances engagement maximization with style preservation

Abstract

Instagram has become a great venue for amateur and professional photographers alike to showcase their work. It has, in other words, democratized photography. Generally, photographers take thousands of photos in a session, from which they pick a few to showcase their work on Instagram. Photographers trying to build a reputation on Instagram have to strike a balance between maximizing their followers' engagement with their photos, while also maintaining their artistic style. We used transfer learning to adapt Xception, which is a model for object recognition trained on the ImageNet dataset, to the task of engagement prediction and utilized Gram matrices generated from VGG19, another object recognition model trained on ImageNet, for the task of style similarity measurement on photos posted on Instagram. Our models can be trained on individual Instagram accounts to create personalized engagement prediction and style similarity models. Once trained on their accounts, users can have new photos sorted based on predicted engagement and style similarity to their previous work, thus enabling them to upload photos that not only have the potential to maximize engagement from their followers but also maintain their style of photography. We trained and validated our models on several Instagram accounts, showing it to be adept at both tasks, also outperforming several baseline models and human annotators.