Cross-Modal Information Retrieval on Flickr30k

Metric: Image-to-text R@1 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Image-to-text R@1▼	Extra Data	Paper	Date↕	Code
1	X2-VLM (large)	98.8	Yes	X$^2$-VLM: All-In-One Pre-trained Model For Visi...	2022-11-22	Code
2	X2-VLM (base)	98.5	Yes	X$^2$-VLM: All-In-One Pre-trained Model For Visi...	2022-11-22	Code
3	BEiT-3	98	Yes	Image as a Foreign Language: BEiT Pretraining fo...	2022-08-22	Code
4	OmniVL (14M)	97.3	Yes	OmniVL:One Foundation Model for Image-Language a...	2022-09-15	-
5	ERNIE-ViL 2.0	97.2	Yes	ERNIE-ViL 2.0: Multi-view Contrastive Learning f...	2022-09-30	Code
6	Aurora (ours, r=128)	97.2	Yes	-	-	-
7	X-VLM (base)	97.1	Yes	Multi-Grained Vision Language Pre-Training: Alig...	2021-11-16	Code
8	VSE-Gradient	97	Yes	Dissecting Deep Metric Learning Losses for Image...	2022-10-21	Code
9	ALIGN	95.3	Yes	Scaling Up Visual and Vision-Language Representa...	2021-02-11	Code
10	ViSTA	89.5	Yes	ViSTA: Vision and Scene Text Aggregation for Cro...	2022-03-31	-
11	IAIS	88.3	Yes	Learning Relation Alignment for Calibrated Cross...	2021-05-28	Code
12	3SHNet	87.1	No	3SHNet: Boosting Image-Sentence Retrieval via Vi...	2024-04-26	Code
13	ViLT-B/32	83.5	Yes	ViLT: Vision-and-Language Transformer Without Co...	2021-02-05	Code
14	DSMD	82.5	No	Dynamic Self-adaptive Multiscale Distillation fr...	2024-04-16	Code
15	RCAR	82.3	No	Plug-and-Play Regulators for Image-Text Matching	2023-03-23	Code
16	NAPReg	79.6	No	-	-	Code
17	SGRAF	77.8	No	Similarity Reasoning and Filtration for Image-Te...	2021-01-05	Code
18	GSMN	76.4	No	A Deep Local and Global Scene-Graph Matching for...	2021-06-04	Code
19	Pearl	75.3	No	-	-	-
20	IMRAM	74.1	No	IMRAM: Iterative Matching with Recurrent Attenti...	2020-03-08	Code
21	SCAN	67.4	No	Stacked Cross Attention for Image-Text Matching	2018-03-21	Code
22	Dual-Path (ResNet)	55.6	No	Dual-Path Convolutional Image-Text Embeddings wi...	2017-11-15	Code
23	SCO (ResNet)	55.5	No	Learning Semantic Concepts and Order for Image a...	2017-12-06	-
24	VSE++ (ResNet)	52.9	No	VSE++: Improving Visual-Semantic Embeddings with...	2017-07-18	Code
25	CMPL (ResNet)	49.6	No	-	-	Code

#1X2-VLM (large)SOTA
98.8
Image-to-text R@1· Extra Data· 2022-11-22
X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks Code
#2X2-VLM (base)
98.5
Image-to-text R@1· Extra Data· 2022-11-22
X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks Code
#3BEiT-3SOTA
98
Image-to-text R@1· Extra Data· 2022-08-22
Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks Code
#4OmniVL (14M)
97.3
Image-to-text R@1· Extra Data· 2022-09-15
OmniVL:One Foundation Model for Image-Language and Video-Language Tasks
#5ERNIE-ViL 2.0
97.2
Image-to-text R@1· Extra Data· 2022-09-30
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training Code
#6Aurora (ours, r=128)
97.2
Image-to-text R@1· Extra Data
No paper
#7X-VLM (base)SOTA
97.1
Image-to-text R@1· Extra Data· 2021-11-16
Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts Code
#8VSE-Gradient
97
Image-to-text R@1· Extra Data· 2022-10-21
Dissecting Deep Metric Learning Losses for Image-Text Retrieval Code
#9ALIGNSOTA
95.3
Image-to-text R@1· Extra Data· 2021-02-11
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision Code
#10ViSTA
89.5
Image-to-text R@1· Extra Data· 2022-03-31
ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval
#11IAIS
88.3
Image-to-text R@1· Extra Data· 2021-05-28
Learning Relation Alignment for Calibrated Cross-modal Retrieval Code
#123SHNet
87.1
Image-to-text R@1· 2024-04-26
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting Code
#13ViLT-B/32SOTA
83.5
Image-to-text R@1· Extra Data· 2021-02-05
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision Code
#14DSMD
82.5
Image-to-text R@1· 2024-04-16
Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Representation Learning Code
#15RCAR
82.3
Image-to-text R@1· 2023-03-23
Plug-and-Play Regulators for Image-Text Matching Code
#16NAPReg
79.6
Image-to-text R@1
No paperCode
#17SGRAFSOTA
77.8
Image-to-text R@1· 2021-01-05
Similarity Reasoning and Filtration for Image-Text Matching Code
#18GSMN
76.4
Image-to-text R@1· 2021-06-04
A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval Code
#19Pearl
75.3
Image-to-text R@1
No paper
#20IMRAMSOTA
74.1
Image-to-text R@1· 2020-03-08
IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval Code
#21SCANSOTA
67.4
Image-to-text R@1· 2018-03-21
Stacked Cross Attention for Image-Text Matching Code
#22Dual-Path (ResNet)SOTA
55.6
Image-to-text R@1· 2017-11-15
Dual-Path Convolutional Image-Text Embeddings with Instance Loss Code
#23SCO (ResNet)
55.5
Image-to-text R@1· 2017-12-06
Learning Semantic Concepts and Order for Image and Sentence Matching
#24VSE++ (ResNet)SOTA
52.9
Image-to-text R@1· 2017-07-18
VSE++: Improving Visual-Semantic Embeddings with Hard Negatives Code
#25CMPL (ResNet)
49.6
Image-to-text R@1
No paperCode