HyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAI超神経

Image To Text Retrieval On Flickr30K

評価指標

Recall@1
Recall@10
Recall@5

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
Recall@1
Recall@10
Recall@5
Paper TitleRepository
InternVL-G-FT (finetuned, w/o ranking)97.9100100InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
UNITER87.399.298HADA: A Graph-based Amalgamation Framework in Image-text Retrieval
BLIP-2 ViT-L (zero-shot, 1K test set)96.9100100BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
ALBEF92.699.999.3HADA: A Graph-based Amalgamation Framework in Image-text Retrieval
ALBEF95.9100.099.8Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
InternVL-C-FT (finetuned, w/o ranking)97.2100100InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
LGSGM7196.191.9A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval
GSMN76.497.394.3A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval
BLIP-2 ViT-G (zero-shot, 1K test set)97.6100100BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
ONE-PEACE (finetuned, w/o ranking)97.6100100ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
ERNIE-ViL 2.096.1100.099.9ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training
0 of 11 row(s) selected.