Image Retrieval with Multi-Modal Query on COCO 2014

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)	96.5	Yes	X$^2$-VLM: All-In-One Pre-trained Model For Visi...	2022-11-22	Code
2	BEiT-3	96.5	Yes	Image as a Foreign Language: BEiT Pretraining fo...	2022-08-22	Code
3	XFM (base)	96.4	Yes	Toward Building General Foundation Models for La...	2023-01-12	Code
4	X2-VLM (base)	96.3	Yes	X$^2$-VLM: All-In-One Pre-trained Model For Visi...	2022-11-22	Code
5	PTP-BLIP (14M)	95.9	Yes	Position-guided Text Prompt for Vision-Language ...	2022-12-19	Code
6	OmniVL (14M)	95.9	Yes	OmniVL:One Foundation Model for Image-Language a...	2022-09-15	-
7	VSE-Gradient	95.6	Yes	Dissecting Deep Metric Learning Losses for Image...	2022-10-21	Code
8	X-VLM (base)	95.6	Yes	Multi-Grained Vision Language Pre-Training: Alig...	2021-11-16	Code
9	Aurora (ours, r=128)	95.3	Yes	-	-	-
10	Florence	95.2	Yes	Florence: A New Foundation Model for Computer Vi...	2021-11-22	Code
11	VK-OOD	95.1	Yes	-	-	Code
12	ALBEF	94.3	Yes	Align before Fuse: Vision and Language Represent...	2021-07-16	Code
13	ERNIE-ViL 2.0	93.6	Yes	ERNIE-ViL 2.0: Multi-view Contrastive Learning f...	2022-09-30	Code
14	ALIGN	93.5	Yes	Scaling Up Visual and Vision-Language Representa...	2021-02-11	Code
15	METER	93.16	Yes	An Empirical Study of Training End-to-End Vision...	2021-11-03	Code
16	TCL	92.8	Yes	Vision-Language Pre-Training with Triple Contras...	2022-02-21	Code
17	M2-Encoder	92.3	No	M2-Encoder: Advancing Bilingual Image-Text Under...	2024-01-29	Code
18	Oscar	92.2	Yes	Oscar: Object-Semantics Aligned Pre-training for...	2020-04-13	Code
19	InternVL-G	91.3	No	InternVL: Scaling up Vision Foundation Models an...	2023-12-21	Code
20	TCL	90.8	No	Vision-Language Pre-Training with Triple Contras...	2022-02-21	Code
21	3SHNet	90.5	No	3SHNet: Boosting Image-Sentence Retrieval via Vi...	2024-04-26	Code
22	ViSTA	90.1	Yes	ViSTA: Vision and Scene Text Aggregation for Cro...	2022-03-31	-
23	PTP-BLIP	90	No	Position-guided Text Prompt for Vision-Language ...	2022-12-19	Code
24	ALBEF	89.5	No	Align before Fuse: Vision and Language Represent...	2021-07-16	Code
25	MaMMUT (ours)	89.1	No	MaMMUT: A Simple Architecture for Joint Learning...	2023-03-29	Code
26	InternVL-C	89	No	InternVL: Scaling up Vision Foundation Models an...	2023-12-21	Code
27	ALADIN	88.6	Yes	ALADIN: Distilling Fine-grained Alignment Scores...	2022-07-29	Code
28	RO-ViT	87.8	No	Region-Aware Pretraining for Open-Vocabulary Obj...	2023-05-11	Code
29	COSMOS ViT-B/16	87.8	No	COSMOS: Cross-Modality Self-Distillation for Vis...	2024-12-02	Code
30	Flamingo	87.3	No	Flamingo: a Visual Language Model for Few-Shot L...	2022-04-29	Code
31	COSMOS ViT-B/32	86.5	No	COSMOS: Cross-Modality Self-Distillation for Vis...	2024-12-02	Code
32	ViLT-B/32	86.3	Yes	ViLT: Vision-and-Language Transformer Without Co...	2021-02-05	Code
33	CoCa	86.2	No	CoCa: Contrastive Captioners are Image-Text Foun...	2022-05-04	Code
34	RCAR	86.1	No	Plug-and-Play Regulators for Image-Text Matching	2023-03-23	Code
35	Florence	85.9	No	Florence: A New Foundation Model for Computer Vi...	2021-11-22	Code
36	ERNIE-ViL 2.0	85.7	No	ERNIE-ViL 2.0: Multi-view Contrastive Learning f...	2022-09-30	Code
37	SGRAF	84.9	No	Similarity Reasoning and Filtration for Image-Te...	2021-01-05	Code
38	IMRAM	83.2	No	IMRAM: Iterative Matching with Recurrent Attenti...	2020-03-08	Code
39	ALIGN	83	No	Scaling Up Visual and Vision-Language Representa...	2021-02-11	Code
40	ViLT-B/32	82.6	No	ViLT: Vision-and-Language Transformer Without Co...	2021-02-05	Code
41	LILE	82.4	No	LILE: Look In-Depth before Looking Elsewhere -- ...	2022-03-02	-
42	SCAN	82.2	No	Stacked Cross Attention for Image-Text Matching	2018-03-21	Code
43	CLIP	81.5	No	Learning Transferable Visual Models From Natural...	2021-02-26	Code
44	VSRN	81.1	No	Visual Semantic Reasoning for Image-Text Matching	2019-09-06	Code
45	DSMD	75.6	No	Dynamic Self-adaptive Multiscale Distillation fr...	2024-04-16	Code
46	PVSE	74.3	No	Polysemous Visual-Semantic Embedding for Cross-M...	2019-06-11	Code
47	SCO (ResNet)	72.3	No	Learning Semantic Concepts and Order for Image a...	2017-12-06	-
48	ImageBERT	71.2	No	ImageBERT: Cross-modal Pre-training with Large-s...	2020-01-22	-
49	Dual-Path (ResNet)	70.5	No	Deep Visual-Semantic Alignments for Generating I...	2014-12-07	Code
50	dfdf	0	No	-	-	-

#1X2-VLM (large)
96.5
Image-to-text R@5· Extra Data· 2022-11-22
X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks Code
#2BEiT-3SOTA
96.5
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
#3XFM (base)
96.4
Image-to-text R@5· Extra Data· 2023-01-12
Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks Code
#4X2-VLM (base)
96.3
Image-to-text R@5· Extra Data· 2022-11-22
X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks Code
#5PTP-BLIP (14M)
95.9
Image-to-text R@5· Extra Data· 2022-12-19
Position-guided Text Prompt for Vision-Language Pre-training Code
#6OmniVL (14M)
95.9
Image-to-text R@5· Extra Data· 2022-09-15
OmniVL:One Foundation Model for Image-Language and Video-Language Tasks
#7VSE-Gradient
95.6
Image-to-text R@5· Extra Data· 2022-10-21
Dissecting Deep Metric Learning Losses for Image-Text Retrieval Code
#8X-VLM (base)SOTA
95.6
Image-to-text R@5· Extra Data· 2021-11-16
Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts Code
#9Aurora (ours, r=128)
95.3
Image-to-text R@5· Extra Data
No paper
#10Florence
95.2
Image-to-text R@5· Extra Data· 2021-11-22
Florence: A New Foundation Model for Computer Vision Code
#11VK-OOD
95.1
Image-to-text R@5· Extra Data
No paperCode
#12ALBEFSOTA
94.3
Image-to-text R@5· Extra Data· 2021-07-16
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation Code
#13ERNIE-ViL 2.0
93.6
Image-to-text R@5· Extra Data· 2022-09-30
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training Code
#14ALIGNSOTA
93.5
Image-to-text R@5· Extra Data· 2021-02-11
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision Code
#15METER
93.16
Image-to-text R@5· Extra Data· 2021-11-03
An Empirical Study of Training End-to-End Vision-and-Language Transformers Code
#16TCL
92.8
Image-to-text R@5· Extra Data· 2022-02-21
Vision-Language Pre-Training with Triple Contrastive Learning Code
#17M2-Encoder
92.3
Image-to-text R@5· 2024-01-29
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining Code
#18OscarSOTA
92.2
Image-to-text R@5· Extra Data· 2020-04-13
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks Code
#19InternVL-G
91.3
Image-to-text R@5· 2023-12-21
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks Code
#20TCL
90.8
Image-to-text R@5· 2022-02-21
Vision-Language Pre-Training with Triple Contrastive Learning Code
#213SHNet
90.5
Image-to-text R@5· 2024-04-26
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting Code
#22ViSTA
90.1
Image-to-text R@5· Extra Data· 2022-03-31
ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval
#23PTP-BLIP
90
Image-to-text R@5· 2022-12-19
Position-guided Text Prompt for Vision-Language Pre-training Code
#24ALBEF
89.5
Image-to-text R@5· 2021-07-16
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation Code
#25MaMMUT (ours)
89.1
Image-to-text R@5· 2023-03-29
MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks Code
#26InternVL-C
89
Image-to-text R@5· 2023-12-21
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks Code
#27ALADIN
88.6
Image-to-text R@5· Extra Data· 2022-07-29
ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval Code
#28RO-ViT
87.8
Image-to-text R@5· 2023-05-11
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers Code
#29COSMOS ViT-B/16
87.8
Image-to-text R@5· 2024-12-02
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Code
#30Flamingo
87.3
Image-to-text R@5· 2022-04-29
Flamingo: a Visual Language Model for Few-Shot Learning Code
#31COSMOS ViT-B/32
86.5
Image-to-text R@5· 2024-12-02
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Code
#32ViLT-B/32
86.3
Image-to-text R@5· Extra Data· 2021-02-05
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision Code
#33CoCa
86.2
Image-to-text R@5· 2022-05-04
CoCa: Contrastive Captioners are Image-Text Foundation Models Code
#34RCAR
86.1
Image-to-text R@5· 2023-03-23
Plug-and-Play Regulators for Image-Text Matching Code
#35Florence
85.9
Image-to-text R@5· 2021-11-22
Florence: A New Foundation Model for Computer Vision Code
#36ERNIE-ViL 2.0
85.7
Image-to-text R@5· 2022-09-30
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training Code
#37SGRAF
84.9
Image-to-text R@5· 2021-01-05
Similarity Reasoning and Filtration for Image-Text Matching Code
#38IMRAMSOTA
83.2
Image-to-text R@5· 2020-03-08
IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval Code
#39ALIGN
83
Image-to-text R@5· 2021-02-11
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision Code
#40ViLT-B/32
82.6
Image-to-text R@5· 2021-02-05
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision Code
#41LILE
82.4
Image-to-text R@5· 2022-03-02
LILE: Look In-Depth before Looking Elsewhere -- A Dual Attention Network using Transformers for Cross-Modal Information Retrieval in Histopathology Archives
#42SCANSOTA
82.2
Image-to-text R@5· 2018-03-21
Stacked Cross Attention for Image-Text Matching Code
#43CLIP
81.5
Image-to-text R@5· 2021-02-26
Learning Transferable Visual Models From Natural Language Supervision Code
#44VSRN
81.1
Image-to-text R@5· 2019-09-06
Visual Semantic Reasoning for Image-Text Matching Code
#45DSMD
75.6
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
#46PVSE
74.3
Image-to-text R@5· 2019-06-11
Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval Code
#47SCO (ResNet)SOTA
72.3
Image-to-text R@5· 2017-12-06
Learning Semantic Concepts and Order for Image and Sentence Matching
#48ImageBERT
71.2
Image-to-text R@5· 2020-01-22
ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data
#49Dual-Path (ResNet)SOTA
70.5
Image-to-text R@5· 2014-12-07
Deep Visual-Semantic Alignments for Generating Image Descriptions Code
#50dfdf
0
Image-to-text R@5
No paper