Saliency Prediction for Mobile User Interfaces
This work addresses the need for accurate saliency prediction in mobile UI design, which is crucial for improving user experience and interface effectiveness, representing a domain-specific advancement rather than a broad breakthrough.
The paper tackles the problem of predicting visual saliency in mobile user interfaces, which differs from natural images, by introducing a novel autoencoder-based multi-scale deep learning model that operates at the element level. The result is a significant performance improvement over existing natural image saliency methods, as demonstrated on established metrics.
We introduce models for saliency prediction for mobile user interfaces. A mobile interface may include elements like buttons, text, etc. in addition to natural images which enable performing a variety of tasks. Saliency in natural images is a well studied area. However, given the difference in what constitutes a mobile interface, and the usage context of these devices, we postulate that saliency prediction for mobile interface images requires a fresh approach. Mobile interface design involves operating on elements, the building blocks of the interface. We first collected eye-gaze data from mobile devices for free viewing task. Using this data, we develop a novel autoencoder based multi-scale deep learning model that provides saliency prediction at the mobile interface element level. Compared to saliency prediction approaches developed for natural images, we show that our approach performs significantly better on a range of established metrics.