1 code implementation • 18 Oct 2023 • Su ah Lee, Seokjin Oh, Woohwan Jung
Although $K$-shot learning techniques can be applied, their performance tends to saturate when the number of annotations exceeds several tens of labels.
no code implementations • 26 Jul 2023 • Seokjin Oh, Su ah Lee, Woohwan Jung
Data augmentation is a technique that enhances the performance of data-hungry models by generating synthetic data instead of collecting new ones.