no code implementations • 3 Feb 2023 • Byounggyu Lew, Donghyun Son, Buru Chang
Although the task-specific knowledge could be learned from source domains by fine-tuning, this hurts the generalization power of pre-trained models due to gradient bias toward the source domains.
1 code implementation • 16 Aug 2022 • Donghyun Son, Byounggyu Lew, Kwanghee Choi, Yongsu Baek, Seungwoo Choi, Beomjun Shin, Sungjoo Ha, Buru Chang
In this study, we formulate real-world scenarios of content moderation and introduce a simple yet effective threshold optimization method that searches the optimal thresholds of the multiple subtasks to make a reliable moderation decision in a cost-effective way.