Image Retrieval with Multi-Modal Query 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	InternVL-G	95.7	No	InternVL: Scaling up Vision Foundation Models an...	2023-12-21	Code
10	ALIGN	95.3	Yes	Scaling Up Visual and Vision-Language Representa...	2021-02-11	Code
11	BEiT-3	94.9	No	Image as a Foreign Language: BEiT Pretraining fo...	2022-08-22	Code
12	InternVL-C	94.7	No	InternVL: Scaling up Vision Foundation Models an...	2023-12-21	Code
13	COSMOS ViT-B/16	92.9	No	COSMOS: Cross-Modality Self-Distillation for Vis...	2024-12-02	Code
14	CoCa	92.5	No	CoCa: Contrastive Captioners are Image-Text Foun...	2022-05-04	Code
15	RO-ViT	92.1	No	Region-Aware Pretraining for Open-Vocabulary Obj...	2023-05-11	Code
16	M2-Encoder	91.2	Yes	M2-Encoder: Advancing Bilingual Image-Text Under...	2024-01-29	Code
17	ERNIE-ViL 2.0	91.2	No	ERNIE-ViL 2.0: Multi-view Contrastive Learning f...	2022-09-30	Code
18	Florence	90.9	No	Florence: A New Foundation Model for Computer Vi...	2021-11-22	Code
19	ALBEF	90.5	No	Align before Fuse: Vision and Language Represent...	2021-07-16	Code
20	COSMOS ViT-B/32	89.9	No	COSMOS: Cross-Modality Self-Distillation for Vis...	2024-12-02	Code
21	ViSTA	89.5	Yes	ViSTA: Vision and Scene Text Aggregation for Cro...	2022-03-31	-
22	Flamingo	89.3	No	Flamingo: a Visual Language Model for Few-Shot L...	2022-04-29	Code
23	VK-OOD	89	No	-	-	Code
24	ALIGN	88.6	No	Scaling Up Visual and Vision-Language Representa...	2021-02-11	Code
25	IAIS	88.3	Yes	Learning Relation Alignment for Calibrated Cross...	2021-05-28	Code
26	CLIP	88	No	Learning Transferable Visual Models From Natural...	2021-02-26	Code
27	3SHNet	87.1	No	3SHNet: Boosting Image-Sentence Retrieval via Vi...	2024-04-26	Code
28	PTP-BLIP (14M)	87.1	No	Position-guided Text Prompt for Vision-Language ...	2022-12-19	Code
29	AltCLIP	86	No	AltCLIP: Altering the Language Encoder in CLIP f...	2022-11-12	Code
30	ViLT-B/32	83.5	Yes	ViLT: Vision-and-Language Transformer Without Co...	2021-02-05	Code
31	DSMD	82.5	No	Dynamic Self-adaptive Multiscale Distillation fr...	2024-04-16	Code
32	RCAR	82.3	No	Plug-and-Play Regulators for Image-Text Matching	2023-03-23	Code
33	UNITER	80.7	No	UNITER: UNiversal Image-TExt Representation Lear...	2019-09-25	Code
34	NAPReg	79.6	No	-	-	Code
35	SGRAF	77.8	No	Similarity Reasoning and Filtration for Image-Te...	2021-01-05	Code
36	GSMN	76.4	No	A Deep Local and Global Scene-Graph Matching for...	2021-06-04	Code
37	Pearl	75.3	No	-	-	-
38	IMRAM	74.1	No	IMRAM: Iterative Matching with Recurrent Attenti...	2020-03-08	Code
39	ViLT-B/32	73.2	No	ViLT: Vision-and-Language Transformer Without Co...	2021-02-05	Code
40	ImageBERT	70.7	No	ImageBERT: Cross-modal Pre-training with Large-s...	2020-01-22	-
41	SCAN	67.4	No	Stacked Cross Attention for Image-Text Matching	2018-03-21	Code
42	Dual-Path (ResNet)	55.6	No	Dual-Path Convolutional Image-Text Embeddings wi...	2017-11-15	Code
43	SCO (ResNet)	55.5	No	Learning Semantic Concepts and Order for Image a...	2017-12-06	-
44	VSE++ (ResNet)	52.9	No	VSE++: Improving Visual-Semantic Embeddings with...	2017-07-18	Code
45	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
#9InternVL-G
95.7
Image-to-text R@1· 2023-12-21
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks Code
#10ALIGNSOTA
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
#11BEiT-3
94.9
Image-to-text R@1· 2022-08-22
Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks Code
#12InternVL-C
94.7
Image-to-text R@1· 2023-12-21
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks Code
#13COSMOS ViT-B/16
92.9
Image-to-text R@1· 2024-12-02
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Code
#14CoCa
92.5
Image-to-text R@1· 2022-05-04
CoCa: Contrastive Captioners are Image-Text Foundation Models Code
#15RO-ViT
92.1
Image-to-text R@1· 2023-05-11
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers Code
#16M2-Encoder
91.2
Image-to-text R@1· Extra Data· 2024-01-29
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining Code
#17ERNIE-ViL 2.0
91.2
Image-to-text R@1· 2022-09-30
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training Code
#18Florence
90.9
Image-to-text R@1· 2021-11-22
Florence: A New Foundation Model for Computer Vision Code
#19ALBEF
90.5
Image-to-text R@1· 2021-07-16
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation Code
#20COSMOS ViT-B/32
89.9
Image-to-text R@1· 2024-12-02
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Code
#21ViSTA
89.5
Image-to-text R@1· Extra Data· 2022-03-31
ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval
#22Flamingo
89.3
Image-to-text R@1· 2022-04-29
Flamingo: a Visual Language Model for Few-Shot Learning Code
#23VK-OOD
89
Image-to-text R@1
No paperCode
#24ALIGN
88.6
Image-to-text R@1· 2021-02-11
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision Code
#25IAIS
88.3
Image-to-text R@1· Extra Data· 2021-05-28
Learning Relation Alignment for Calibrated Cross-modal Retrieval Code
#26CLIP
88
Image-to-text R@1· 2021-02-26
Learning Transferable Visual Models From Natural Language Supervision Code
#273SHNet
87.1
Image-to-text R@1· 2024-04-26
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting Code
#28PTP-BLIP (14M)
87.1
Image-to-text R@1· 2022-12-19
Position-guided Text Prompt for Vision-Language Pre-training Code
#29AltCLIP
86
Image-to-text R@1· 2022-11-12
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities Code
#30ViLT-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
#31DSMD
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
#32RCAR
82.3
Image-to-text R@1· 2023-03-23
Plug-and-Play Regulators for Image-Text Matching Code
#33UNITERSOTA
80.7
Image-to-text R@1· 2019-09-25
UNITER: UNiversal Image-TExt Representation Learning Code
#34NAPReg
79.6
Image-to-text R@1
No paperCode
#35SGRAF
77.8
Image-to-text R@1· 2021-01-05
Similarity Reasoning and Filtration for Image-Text Matching Code
#36GSMN
76.4
Image-to-text R@1· 2021-06-04
A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval Code
#37Pearl
75.3
Image-to-text R@1
No paper
#38IMRAM
74.1
Image-to-text R@1· 2020-03-08
IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval Code
#39ViLT-B/32
73.2
Image-to-text R@1· 2021-02-05
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision Code
#40ImageBERT
70.7
Image-to-text R@1· 2020-01-22
ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data
#41SCANSOTA
67.4
Image-to-text R@1· 2018-03-21
Stacked Cross Attention for Image-Text Matching Code
#42Dual-Path (ResNet)SOTA
55.6
Image-to-text R@1· 2017-11-15
Dual-Path Convolutional Image-Text Embeddings with Instance Loss Code
#43SCO (ResNet)
55.5
Image-to-text R@1· 2017-12-06
Learning Semantic Concepts and Order for Image and Sentence Matching
#44VSE++ (ResNet)SOTA
52.9
Image-to-text R@1· 2017-07-18
VSE++: Improving Visual-Semantic Embeddings with Hard Negatives Code
#45CMPL (ResNet)
49.6
Image-to-text R@1
No paperCode