ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrieval
This work addresses the problem of interactive image retrieval for users needing to search images through conversations, representing an incremental advancement in multimodal retrieval systems.
The authors tackled general conversational image retrieval by curating the ChatSearch dataset with multi-round multimodal conversational queries and proposing the ChatSearcher model, which achieved superior performance on ChatSearch and competitive results on other tasks.
In this paper, we investigate the task of general conversational image retrieval on open-domain images. The objective is to search for images based on interactive conversations between humans and computers. To advance this task, we curate a dataset called ChatSearch. This dataset includes a multi-round multimodal conversational context query for each target image, thereby requiring the retrieval system to find the accurate image from database. Simultaneously, we propose a generative retrieval model named ChatSearcher, which is trained end-to-end to accept/produce interleaved image-text inputs/outputs. ChatSearcher exhibits strong capability in reasoning with multimodal context and can leverage world knowledge to yield visual retrieval results. It demonstrates superior performance on the ChatSearch dataset and also achieves competitive results on other image retrieval tasks and visual conversation tasks. We anticipate that this work will inspire further research on interactive multimodal retrieval systems. Our dataset will be available at https://github.com/joez17/ChatSearch.