The growing proliferation of customized and pretrained generative models has made it infeasible for a user to be fully cognizant of every model in existence. To address this need, we introduce the task of content-based model search: given a query and a large set of generative models, finding the models that best match the query. As each generative model produces a distribution of images, we formulate the search task as an optimization problem to select the model with the highest probability of generating similar content as the query. We introduce a formulation to approximate this probability given the query from different modalities, e.g., image, sketch, and text. Furthermore, we propose a contrastive learning framework for model retrieval, which learns to adapt features for various query modalities. We demonstrate that our method outperforms several baselines on Generative Model Zoo, a new benchmark we create for the model retrieval task.
@article{arxiv.2210.03116,
title = {Content-Based Search for Deep Generative Models},
author = {Daohan Lu and Sheng-Yu Wang and Nupur Kumari and Rohan Agarwal and Mia Tang and David Bau and Jun-Yan Zhu},
journal= {arXiv preprint arXiv:2210.03116},
year = {2023}
}
Comments
Our project page is hosted at https://generative-intelligence-lab.github.io/modelverse/