Content-Based Search for Deep Generative Models
This addresses the challenge for users in efficiently discovering relevant generative models from a large set, though it is incremental as it builds on existing retrieval and contrastive learning techniques.
The paper tackles the problem of finding generative models that match a query from various modalities by formulating content-based model search as an optimization problem and proposing a contrastive learning framework, demonstrating superior performance on a new benchmark.
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.