Cross Modal Retrieval On Flickr30K

评估指标

Image-to-text R@1

Image-to-text R@10

Image-to-text R@5

Text-to-image R@1

Text-to-image R@10

Text-to-image R@5

评测结果

各个模型在此基准测试上的表现结果

							Paper Title	Repository
ERNIE-ViL 2.0	97.2	100.0	100.0	93.3	99.8	99.4	ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training
X2-VLM (large)	98.8	100	100	91.8	99.5	98.6	X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
VAST	-	-	-	91.0	99.5	98.5	VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
X2-VLM (base)	98.5	100	100	90.4	99.3	98.2	X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
BEiT-3	98.0	100.0	100.0	90.3	99.5	98.7	Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks
OmniVL (14M)	97.3	100	99.9	87.9	99.1	97.8	OmniVL:One Foundation Model for Image-Language and Video-Language Tasks	-
X-VLM (base)	97.1	100.0	100.0	86.9	98.7	97.3	Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
Aurora (ours, r=128)	97.2	100	100	86.8	98.9	97.6	-	-
VSE-Gradient	97.0	100	99.6	86.3	99.0	97.4	Dissecting Deep Metric Learning Losses for Image-Text Retrieval
ALIGN	95.3	100	99.8	84.9	98.6	97.4	Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
IAIS	88.3	99.4	98.4	76.86	95.72	93.3	Learning Relation Alignment for Calibrated Cross-modal Retrieval
ViSTA	89.5	99.6	98.4	75.8	96.9	94.2	ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval	-
3SHNet	87.1	99.2	98.2	69.5	94.7	91.0	3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting
DSMD	82.5	97.7	95.5	68.4	94.4	90.8	Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Representation Learning
ViLT-B/32	83.5	98.6	96.7	64.4	93.8	88.7	ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
RCAR	82.3	98.4	96.0	62.6	91.1	85.8	Plug-and-Play Regulators for Image-Text Matching
NAPReg	79.6	-	-	60.0	-	-	NAPReg: Nouns As Proxies Regularization for Semantically Aware Cross-Modal Embeddings	-
SGRAF	77.8	97.4	94.1	58.5	88.8	83.0	Similarity Reasoning and Filtration for Image-Text Matching
GSMN	76.4	97.3	94.3	57.4	89.0	82.3	Graph Structured Network for Image-Text Matching
Pearl	75.3	97.3	93.4	54.98	88.26	81.3	-	-

0 of 27 row(s) selected.