Search Results for author:
Found 2 papers, 1 papers with code
Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images
We present a new framework leveraging off-the-shelf generative models to generate synthetic training images, addressing multiple challenges: class name ambiguity, lack of diversity in naive prompts, and domain shifts.
Similarity Search for Efficient Active Learning and Search of Rare Concepts
Many active learning and search approaches are intractable for large-scale industrial settings with billions of unlabeled examples.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
