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

arXiv:2405.05695v1 Announce Type: new
Abstract: 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 with a flexible asymmetric structure for the primary and auxiliary tasks, which produces different networks for training and inference. Specifically, starting from two single task …

arxiv cost cs.ai cs.cv cs.lg extra inference labels nas stat.ml type