Identifying Auxiliary or Adversarial Tasks Using Necessary Condition Analysis for Adversarial Multi-task Video Understanding

no code implementations • 22 Aug 2022 • Stephen Su, Samuel Kwong, Qingyu Zhao, De-An Huang, Juan Carlos Niebles, Ehsan Adeli

In this work, we propose a generalized notion of multi-task learning by incorporating both auxiliary tasks that the model should perform well on and adversarial tasks that the model should not perform well on.

Action Recognition Multi-Task Learning +3