Mutual Information Divergence: A Unified Metric for Multimodal Generative Models

arXiv2205.13445MaRDI QIDQ6400271FDOQ6400271

Authors: Jin-Hwa Kim, Yunji Kim, Jiyoung Lee, Kang Min Yoo, Sang-Woo Lee 

Publication date: 25 May 2022

Abstract: Text-to-image generation and image captioning are recently emerged as a new experimental paradigm to assess machine intelligence. They predict continuous quantity accompanied by their sampling techniques in the generation, making evaluation complicated and intractable to get marginal distributions. Based on a recent trend that multimodal generative evaluations exploit a vison-and-language pre-trained model, we propose the negative Gaussian cross-mutual information using the CLIP features as a unified metric, coined by Mutual Information Divergence (MID). To validate, we extensively compare it with competing metrics using carefully-generated or human-annotated judgments in text-to-image generation and image captioning tasks. The proposed MID significantly outperforms the competitive methods by having consistency across benchmarks, sample parsimony, and robustness toward the exploited CLIP model. We look forward to seeing the underrepresented implications of the Gaussian cross-mutual information in multimodal representation learning and the future works based on this novel proposition.

Has companion code repository: https://github.com/naver-ai/mid.metric

This page was built for publication: Mutual Information Divergence: A Unified Metric for Multimodal Generative Models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6400271)