Papers › BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language...

BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

28 Jan 2022arXiv:2201.12086archive 2025-07-28

Junnan Li, Dongxu Li, Caiming Xiong, Steven Hoi

Vision-Language Pre-training (VLP) has advanced the performance for many vision-language tasks. However, most existing pre-trained models only excel in either understanding-based tasks or generation-based tasks. Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image-text pairs collected from the web, which is a suboptimal source of supervision. In this paper, we propose BLIP, a new VLP framework which transfers flexibly to both vision-language understanding and generation tasks. BLIP effectively utilizes the noisy web data by bootstrapping the captions, where a captioner generates synthetic captions and a filter removes the noisy ones. We achieve state-of-the-art results on a wide range of vision-language tasks, such as image-text retrieval (+2.7% in average recall@1), image captioning (+2.8% in CIDEr), and VQA (+1.6% in VQA score). BLIP also demonstrates strong generalization ability when directly transferred to video-language tasks in a zero-shot manner. Code, models, and datasets are released at https://github.com/salesforce/BLIP.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

salesforce/lavis officialmentioned on GitHubpytorchBSD-3-Clause report
salesforce/blip mentioned in papermentioned on GitHubpytorchBSD-3-Clause report
huggingface/transformers mentioned on GitHubpytorch report
ninatu/howtocaption mentioned on GitHubpytorchNOASSERTION report
pwc-1/Paper-8 mindspore report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image CaptioningImage-text RetrievalImage-text matchingOpen Vocabulary Attribute DetectionRetrievalText RetrievalVisual Question Answering (VQA)Visual Reasoning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Captioning nocaps-val-in-domain BLIP_ViT-L CIDEr 114.9 #5 of 11 Archive leaderboard report
Image Captioning nocaps-val-in-domain BLIP_ViT-L Pre-train (#images) 129M #5 of 11 Archive leaderboard report
Image Captioning nocaps-val-in-domain BLIP_ViT-L SPICE 15.2 #5 of 11 Archive leaderboard report
Image Captioning nocaps-val-in-domain BLIP_CapFilt-L CIDEr 111.8 #7 of 11 Archive leaderboard report
Image Captioning nocaps-val-in-domain BLIP_CapFilt-L Pre-train (#images) 129M #7 of 11 Archive leaderboard report
Image Captioning nocaps-val-in-domain BLIP_CapFilt-L SPICE 14.9 #7 of 11 Archive leaderboard report
Image Captioning nocaps-val-near-domain BLIP_ViT-L CIDEr 112.1 #5 of 10 Archive leaderboard report
Image Captioning nocaps-val-near-domain BLIP_ViT-L Pre-train (#images) 129M #5 of 10 Archive leaderboard report
Image Captioning nocaps-val-near-domain BLIP_ViT-L SPICE 14.9 #5 of 10 Archive leaderboard report
Image Captioning nocaps-val-near-domain BLIP_CapFilt-L CIDEr 108.6 #7 of 10 Archive leaderboard report
Image Captioning nocaps-val-near-domain BLIP_CapFilt-L Pre-train (#images) 129M #7 of 10 Archive leaderboard report
Image Captioning nocaps-val-near-domain BLIP_CapFilt-L SPICE 14.8 #7 of 10 Archive leaderboard report
Image Captioning nocaps-val-out-domain BLIP_ViT-L CIDEr 115.3 #4 of 10 Archive leaderboard report
Image Captioning nocaps-val-out-domain BLIP_ViT-L Pretrain (#images) 129M #4 of 10 Archive leaderboard report
Image Captioning nocaps-val-out-domain BLIP_ViT-L SPICE 14.4 #4 of 10 Archive leaderboard report
Image Captioning nocaps-val-out-domain BLIP_CapFilt-L CIDEr 111.5 #6 of 10 Archive leaderboard report
Image Captioning nocaps-val-out-domain BLIP_CapFilt-L Pretrain (#images) 129M #6 of 10 Archive leaderboard report
Image Captioning nocaps-val-out-domain BLIP_CapFilt-L SPICE 14.2 #6 of 10 Archive leaderboard report
Image Captioning nocaps-val-overall BLIP_ViT-L CIDEr 113.2 #5 of 11 Archive leaderboard report
Image Captioning nocaps-val-overall BLIP_ViT-L Pretrain (#images) 129M #5 of 11 Archive leaderboard report
Image Captioning nocaps-val-overall BLIP_ViT-L SPICE 14.8 #5 of 11 Archive leaderboard report
Image Captioning nocaps-val-overall BLIP_CapFilt-L CIDEr 109.6 #7 of 11 Archive leaderboard report
Image Captioning nocaps-val-overall BLIP_CapFilt-L Pretrain (#images) 129M #7 of 11 Archive leaderboard report
Image Captioning nocaps-val-overall BLIP_CapFilt-L SPICE 14.7 #7 of 11 Archive leaderboard report
Image-text matching CommercialAdsDataset BLIP ADD(S) AUC 83.51 #6 of 8 Archive leaderboard report
Open Vocabulary Attribute Detection OVAD-Box benchmark BLIP mean average precision 24.3 #3 of 7 Archive leaderboard report
Visual Reasoning NLVR2 Test BLIP-129M Accuracy 83.09 #9 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: BLIP

BLIP

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections