PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 11, 2023409 citationsOpen Access

InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

WDWenliang DaiShanghai Jiao Tong UniversityJLJunnan LiNational University of SingaporeDLDongxu LiXiamen University

Key Points

Key points are not available for this paper at this time.

Abstract

Large-scale pre-training and instruction tuning have been successful at creating general-purpose language models with broad competence. However, building general-purpose vision-language models is challenging due to the rich input distributions and task diversity resulting from the additional visual input. Although vision-language pretraining has been widely studied, vision-language instruction tuning remains under-explored. In this paper, we conduct a systematic and comprehensive study on vision-language instruction tuning based on the pretrained BLIP-2 models. We gather 26 publicly available datasets, covering a wide variety of tasks and capabilities, and transform them into instruction tuning format. Additionally, we introduce an instruction-aware Query Transformer, which extracts informative features tailored to the given instruction. Trained on 13 held-in datasets, InstructBLIP attains state-of-the-art zero-shot performance across all 13 held-out datasets, substantially outperforming BLIP-2 and larger Flamingo models. Our models also lead to state-of-the-art performance when finetuned on individual downstream tasks (e.g., 90.7% accuracy on ScienceQA questions with image contexts). Furthermore, we qualitatively demonstrate the advantages of InstructBLIP over concurrent multimodal models. All InstructBLIP models are open-sourced at https://github.com/salesforce/LAVIS/tree/main/projects/instructblip.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Dai et al. (2023) studied this question.

synapsesocial.com/papers/6a08c2138bd2868868ba024chttps://doi.org/10.48550/arxiv.2305.06500
Ask AI
Helpful
Bookmark
Share
View Full Paper