Multi-Task Learning by Deep Collaboration and Application in Facial Landmark Detection
This addresses data scarcity in vision domains like facial analysis, but it is incremental as it builds on existing multi-task learning methods.
The paper tackles data scarcity in CNNs for vision tasks by proposing a novel soft-parameter sharing mechanism called Deep Collaboration for multi-task learning, which improves accuracy in facial landmark detection by leveraging task-specific features at various depths.
Convolutional neural networks (CNNs) have become the most successful approach in many vision-related domains. However, they are limited to domains where data is abundant. Recent works have looked at multi-task learning (MTL) to mitigate data scarcity by leveraging domain-specific information from related tasks. In this paper, we present a novel soft-parameter sharing mechanism for CNNs in a MTL setting, which we refer to as Deep Collaboration. We propose taking into account the notion that task relevance depends on depth by using lateral transformation blocs with skip connections. This allows extracting task-specific features at various depth without sacrificing features relevant to all tasks. We show that CNNs connected with our Deep Collaboration obtain better accuracy on facial landmark detection with related tasks. We finally verify that our approach effectively allows knowledge sharing by showing depth-specific influence of tasks that we know are related.