Image Retrieval with Multi-Modal Query on Flickr30k

Metric: Image-to-text R@5 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Image-to-text R@5▼	Extra Data	Paper	Date↕	Code
1	X2-VLM (large)	100	Yes	X$^2$-VLM: All-In-One Pre-trained Model For Visi...	2022-11-22	Code
2	X2-VLM (base)	100	Yes	X$^2$-VLM: All-In-One Pre-trained Model For Visi...	2022-11-22	Code
3	BEiT-3	100	Yes	Image as a Foreign Language: BEiT Pretraining fo...	2022-08-22	Code
4	ERNIE-ViL 2.0	100	Yes	ERNIE-ViL 2.0: Multi-view Contrastive Learning f...	2022-09-30	Code
5	Aurora (ours, r=128)	100	Yes	-	-	-
6	X-VLM (base)	100	Yes	Multi-Grained Vision Language Pre-Training: Alig...	2021-11-16	Code
7	OmniVL (14M)	99.9	Yes	OmniVL:One Foundation Model for Image-Language a...	2022-09-15	-
8	BEiT-3	99.9	No	Image as a Foreign Language: BEiT Pretraining fo...	2022-08-22	Code
9	ALIGN	99.8	Yes	Scaling Up Visual and Vision-Language Representa...	2021-02-11	Code
10	InternVL-G	99.7	No	InternVL: Scaling up Vision Foundation Models an...	2023-12-21	Code
11	VSE-Gradient	99.6	Yes	Dissecting Deep Metric Learning Losses for Image...	2022-10-21	Code
12	InternVL-C	99.6	No	InternVL: Scaling up Vision Foundation Models an...	2023-12-21	Code
13	CoCa	99.5	No	CoCa: Contrastive Captioners are Image-Text Foun...	2022-05-04	Code
14	COSMOS ViT-B/16	99.4	No	COSMOS: Cross-Modality Self-Distillation for Vis...	2024-12-02	Code
15	RO-ViT	99.4	No	Region-Aware Pretraining for Open-Vocabulary Obj...	2023-05-11	Code
16	OpenCLIP VIT-H/14	99.3	No	Reproducible scaling laws for contrastive langua...	2022-12-14	Code
17	M2-Encoder	99.2	Yes	M2-Encoder: Advancing Bilingual Image-Text Under...	2024-01-29	Code
18	VK-OOD	99.2	No	-	-	Code
19	ERNIE-ViL 2.0	99.1	No	ERNIE-ViL 2.0: Multi-view Contrastive Learning f...	2022-09-30	Code
20	Florence	99.1	No	Florence: A New Foundation Model for Computer Vi...	2021-11-22	Code
21	ALBEF	98.8	No	Align before Fuse: Vision and Language Represent...	2021-07-16	Code
22	COSMOS ViT-B/32	98.8	No	COSMOS: Cross-Modality Self-Distillation for Vis...	2024-12-02	Code
23	Flamingo	98.8	No	Flamingo: a Visual Language Model for Few-Shot L...	2022-04-29	Code
24	ALIGN	98.7	No	Scaling Up Visual and Vision-Language Representa...	2021-02-11	Code
25	CLIP	98.7	No	Learning Transferable Visual Models From Natural...	2021-02-26	Code
26	ViSTA	98.4	Yes	ViSTA: Vision and Scene Text Aggregation for Cro...	2022-03-31	-
27	IAIS	98.4	Yes	Learning Relation Alignment for Calibrated Cross...	2021-05-28	Code
28	PTP-BLIP (14M)	98.4	No	Position-guided Text Prompt for Vision-Language ...	2022-12-19	Code
29	3SHNet	98.2	No	3SHNet: Boosting Image-Sentence Retrieval via Vi...	2024-04-26	Code
30	AltCLIP	98	No	AltCLIP: Altering the Language Encoder in CLIP f...	2022-11-12	Code
31	ViLT-B/32	96.7	Yes	ViLT: Vision-and-Language Transformer Without Co...	2021-02-05	Code
32	RCAR	96	No	Plug-and-Play Regulators for Image-Text Matching	2023-03-23	Code
33	UNITER	95.7	No	UNITER: UNiversal Image-TExt Representation Lear...	2019-09-25	Code
34	DSMD	95.5	No	Dynamic Self-adaptive Multiscale Distillation fr...	2024-04-16	Code
35	GSMN	94.3	No	A Deep Local and Global Scene-Graph Matching for...	2021-06-04	Code
36	SGRAF	94.1	No	Similarity Reasoning and Filtration for Image-Te...	2021-01-05	Code
37	ViLT-B/32	93.6	No	ViLT: Vision-and-Language Transformer Without Co...	2021-02-05	Code
38	Pearl	93.4	No	-	-	-
39	IMRAM	93	No	IMRAM: Iterative Matching with Recurrent Attenti...	2020-03-08	Code
40	SCAN	90.3	No	Stacked Cross Attention for Image-Text Matching	2018-03-21	Code
41	ImageBERT	90.2	No	ImageBERT: Cross-modal Pre-training with Large-s...	2020-01-22	-
42	SCO (ResNet)	82	No	Learning Semantic Concepts and Order for Image a...	2017-12-06	-
43	Dual-Path (ResNet)	81.9	No	Dual-Path Convolutional Image-Text Embeddings wi...	2017-11-15	Code
44	VSE++ (ResNet)	80.5	No	VSE++: Improving Visual-Semantic Embeddings with...	2017-07-18	Code
45	CMPL (ResNet)	76.8	No	-	-	Code

#1X2-VLM (large)
100
Image-to-text R@5· Extra Data· 2022-11-22
X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks Code
#2X2-VLM (base)
100
Image-to-text R@5· Extra Data· 2022-11-22
X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks Code
#3BEiT-3
100
Image-to-text R@5· Extra Data· 2022-08-22
Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks Code
#4ERNIE-ViL 2.0
100
Image-to-text R@5· Extra Data· 2022-09-30
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training Code
#5Aurora (ours, r=128)
100
Image-to-text R@5· Extra Data
No paper
#6X-VLM (base)SOTA
100
Image-to-text R@5· Extra Data· 2021-11-16
Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts Code
#7OmniVL (14M)
99.9
Image-to-text R@5· Extra Data· 2022-09-15
OmniVL:One Foundation Model for Image-Language and Video-Language Tasks
#8BEiT-3
99.9
Image-to-text R@5· 2022-08-22
Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks Code
#9ALIGNSOTA
99.8
Image-to-text R@5· Extra Data· 2021-02-11
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision Code
#10InternVL-G
99.7
Image-to-text R@5· 2023-12-21
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks Code
#11VSE-Gradient
99.6
Image-to-text R@5· Extra Data· 2022-10-21
Dissecting Deep Metric Learning Losses for Image-Text Retrieval Code
#12InternVL-C
99.6
Image-to-text R@5· 2023-12-21
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks Code
#13CoCa
99.5
Image-to-text R@5· 2022-05-04
CoCa: Contrastive Captioners are Image-Text Foundation Models Code
#14COSMOS ViT-B/16
99.4
Image-to-text R@5· 2024-12-02
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Code
#15RO-ViT
99.4
Image-to-text R@5· 2023-05-11
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers Code
#16OpenCLIP VIT-H/14
99.3
Image-to-text R@5· 2022-12-14
Reproducible scaling laws for contrastive language-image learning Code
#17M2-Encoder
99.2
Image-to-text R@5· Extra Data· 2024-01-29
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining Code
#18VK-OOD
99.2
Image-to-text R@5
No paperCode
#19ERNIE-ViL 2.0
99.1
Image-to-text R@5· 2022-09-30
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training Code
#20Florence
99.1
Image-to-text R@5· 2021-11-22
Florence: A New Foundation Model for Computer Vision Code
#21ALBEF
98.8
Image-to-text R@5· 2021-07-16
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation Code
#22COSMOS ViT-B/32
98.8
Image-to-text R@5· 2024-12-02
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Code
#23Flamingo
98.8
Image-to-text R@5· 2022-04-29
Flamingo: a Visual Language Model for Few-Shot Learning Code
#24ALIGN
98.7
Image-to-text R@5· 2021-02-11
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision Code
#25CLIP
98.7
Image-to-text R@5· 2021-02-26
Learning Transferable Visual Models From Natural Language Supervision Code
#26ViSTA
98.4
Image-to-text R@5· Extra Data· 2022-03-31
ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval
#27IAIS
98.4
Image-to-text R@5· Extra Data· 2021-05-28
Learning Relation Alignment for Calibrated Cross-modal Retrieval Code
#28PTP-BLIP (14M)
98.4
Image-to-text R@5· 2022-12-19
Position-guided Text Prompt for Vision-Language Pre-training Code
#293SHNet
98.2
Image-to-text R@5· 2024-04-26
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting Code
#30AltCLIP
98
Image-to-text R@5· 2022-11-12
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities Code
#31ViLT-B/32SOTA
96.7
Image-to-text R@5· Extra Data· 2021-02-05
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision Code
#32RCAR
96
Image-to-text R@5· 2023-03-23
Plug-and-Play Regulators for Image-Text Matching Code
#33UNITERSOTA
95.7
Image-to-text R@5· 2019-09-25
UNITER: UNiversal Image-TExt Representation Learning Code
#34DSMD
95.5
Image-to-text R@5· 2024-04-16
Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Representation Learning Code
#35GSMN
94.3
Image-to-text R@5· 2021-06-04
A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval Code
#36SGRAF
94.1
Image-to-text R@5· 2021-01-05
Similarity Reasoning and Filtration for Image-Text Matching Code
#37ViLT-B/32
93.6
Image-to-text R@5· 2021-02-05
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision Code
#38Pearl
93.4
Image-to-text R@5
No paper
#39IMRAM
93
Image-to-text R@5· 2020-03-08
IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval Code
#40SCANSOTA
90.3
Image-to-text R@5· 2018-03-21
Stacked Cross Attention for Image-Text Matching Code
#41ImageBERT
90.2
Image-to-text R@5· 2020-01-22
ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data
#42SCO (ResNet)SOTA
82
Image-to-text R@5· 2017-12-06
Learning Semantic Concepts and Order for Image and Sentence Matching
#43Dual-Path (ResNet)SOTA
81.9
Image-to-text R@5· 2017-11-15
Dual-Path Convolutional Image-Text Embeddings with Instance Loss Code
#44VSE++ (ResNet)SOTA
80.5
Image-to-text R@5· 2017-07-18
VSE++: Improving Visual-Semantic Embeddings with Hard Negatives Code
#45CMPL (ResNet)
76.8
Image-to-text R@5
No paperCode