Accurate face detection and subsequent localization of facial landmarks are mandatory steps in many computer vision applications, such as emotion recognition, age estimation, and gender identification. Thanks to advancements in deep learning, numerous facial applications have been developed for human faces. However, most of these applications require multiple models to accomplish several tasks simultaneously, leading to increased memory usage and longer inference times. Additionally, less attention has been paid to other domains, such as animals and cartoon characters.

To address these challenges, the authors propose an input-agnostic face model, AnyFace++, designed to perform multiple face-related tasks concurrently. The tasks include face detection and prediction of facial landmarks for human, animal, and cartoon faces, as well as age estimation, gender classification, and emotion recognition for human faces. They trained the model using deep multi-task, multi-domain learning with a heterogeneous cost function. The experimental results demonstrate that AnyFace++ produces outcomes comparable to cutting-edge models designed for specific domains.