Low-Cost Transfer Learning of Face Tasks
This addresses the problem of efficient knowledge transfer across face-related tasks for researchers and practitioners, but it appears incremental as it builds on existing pretrained networks and filter analysis.
The paper tackled the problem of understanding what different filters in a face recognition network represent and whether this information can be used to train other face-related tasks like age, head pose, and emotion without traditional transfer learning, resulting in a method to infer which tasks the network generalizes for and the best way to transfer knowledge.
Do we know what the different filters of a face network represent? Can we use this filter information to train other tasks without transfer learning? For instance, can age, head pose, emotion and other face related tasks be learned from face recognition network without transfer learning? Understanding the role of these filters allows us to transfer knowledge across tasks and take advantage of large data sets in related tasks. Given a pretrained network, we can infer which tasks the network generalizes for and the best way to transfer the information to a new task.