Skip to content

Search Engine that supports multiple embedding neural networks on multimodal data

Notifications You must be signed in to change notification settings

cooliotonyio/dime

Repository files navigation

DIME (Dataset, Index, Model, Embedding)

An Online Tool for the Visual Comparison of Cross-Modal Retrieval Models

Paper link: https://doi.org/10.1007/978-3-030-37734-2_61

Abstract

Cross-modal retrieval relies on accurate models to retrieve relevant results for queries across modalities such as image, text, and video. In this paper, we build upon previous work by tackling the difficulty of evaluating models both quantitatively and qualitatively quickly. We present DIME (Dataset, Index, Model, Embedding), a modality-agnostic tool that handles multimodal datasets, trained models, and data preprocessors to support straightforward model comparison with a web browser graphical user interface. DIME inherently supports building modality-agnostic queryable indexes and extraction of relevant feature embeddings, and thus effectively doubles as an efficient cross-modal tool to explore and search through datasets.

About

Search Engine that supports multiple embedding neural networks on multimodal data

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published