Ask a Question

Prefer a chat interface with context about you and your work?

Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost

Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost

We aim at exploiting additional auxiliary labels from an independent (auxiliary) task to boost the primary task performance which we focus on, while preserving a single task inference cost of the primary task. While most existing auxiliary learning methods are optimization-based relying on loss weights/gradients manipulation, our method is architecture-based …