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 …