ML Research Wiki / Benchmarks / Image Retrieval / Flickr30k

Flickr30k

Image Retrieval Benchmark

Performance Over Time

📊 Showing 9 results | 📏 Metric: Recall@10

Top Performing Models

Rank Model Paper Recall@10 Date Code
1 BLIP-2 ViT-G (zero-shot, 1K test set) BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models 98.10 2023-01-30 📦 huggingface/transformers 📦 salesforce/lavis 📦 thudm/visualglm-6b
2 BLIP-2 ViT-L (zero-shot, 1K test set) BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models 97.60 2023-01-30 📦 huggingface/transformers 📦 salesforce/lavis 📦 thudm/visualglm-6b
3 MaMMUT (ours) MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks 96.00 2023-03-29 📦 lucidrains/mammut-pytorch
4 HADA HADA: A Graph-based Amalgamation Framework in Image-text Retrieval 95.94 2023-01-11 📦 m2man/hada 📦 m2man/HADA-LAVIS
5 ALBEF HADA: A Graph-based Amalgamation Framework in Image-text Retrieval 95.30 2023-01-11 📦 m2man/hada 📦 m2man/HADA-LAVIS
6 UNITER HADA: A Graph-based Amalgamation Framework in Image-text Retrieval 94.08 2023-01-11 📦 m2man/hada 📦 m2man/HADA-LAVIS
7 LGSGM A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval 84.10 2021-06-04 📦 m2man/LGSGM
8 GSMN A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval 82.30 2021-06-04 📦 m2man/LGSGM
9 VisualSparta VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words 82.00 2021-01-01 📦 soco-ai/SF-QA

All Papers (9)

huggingface/transformers salesforce/lavis
huggingface/transformers salesforce/lavis
lucidrains/mammut-pytorch
m2man/hada m2man/HADA-LAVIS
m2man/hada m2man/HADA-LAVIS
m2man/hada m2man/HADA-LAVIS
m2man/LGSGM
m2man/LGSGM
soco-ai/SF-QA