Automated Search for Resource-Efficient Branched Multi-Task Networks

Understand

The multi-modal nature of many vision problems calls for neural network architectures that can perform multiple tasks concurrently.

• Typically, such architectures have been handcrafted in the literature.
• However, given the size and complexity of the problem, this manual architecture exploration likely exceeds human design abilities.
• In this paper, we propose a principled approach, rooted in differentiable neural architecture search, to automatically define branching (tree-like) structures in the encoding stage of a multi-task neural network.