Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Computer Vision
/
Image Retrieval
/
CIRR
Image Retrieval on CIRR
Metric: R@5 (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Export CSV
Sort:
R@5 (best first)
R@5 (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
R@5
▼
Extra Data
Paper
Date
↕
Code
1
CoVR-BLIP-2
81.08
No
CoVR-2: Automatic Data Construction for Composed...
2023-08-28
Code
2
CoVR-BLIP-2
73.61
No
CoVR-2: Automatic Data Construction for Composed...
2023-08-28
Code
3
IP-CIR + LDRE (CLIP G/14)
70.07
No
Imagine and Seek: Improving Composed Image Retri...
2024-11-24
-
4
SEIZE (CLIP G/14)
69.42
No
-
-
Code
5
TransAgg (Laion-CIR-Combined)
68.88
No
Zero-shot Composed Text-Image Retrieval
2023-06-12
Code
6
ImageScope (CLIP-ViT-L/14)
67.54
No
ImageScope: Unifying Language-Guided Image Retri...
2025-03-13
Code
7
RTD + LinCIR (CLIP G/14)
67.47
No
An Efficient Post-hoc Framework for Reducing Tas...
2024-06-13
Code
8
OSrCIR (CLIP G/14)
67.25
No
Reason-before-Retrieve: One-Stage Reflective Cha...
2024-12-15
Code
9
MagicLens (CoCa L)
67
No
MagicLens: Self-Supervised Image Retrieval with ...
2024-03-28
Code
10
LDRE (CLIP G/14)
66.39
No
-
-
Code
11
SPN4CIR (SPN-CC)
65.42
No
Improving Composed Image Retrieval via Contrasti...
2024-04-17
Code
12
LinCIR (CLIP G/14)
64.72
No
Language-only Efficient Training of Zero-shot Co...
2023-12-04
Code
13
SCOT (WACV 2025)
64.34
No
SCOT: Self-Supervised Contrastive Pretraining Fo...
2025-01-12
-
14
CIReVL (CLIP G/14)
64.29
No
Vision-by-Language for Training-Free Composition...
2023-10-13
Code
15
MagicLens (CoCa B)
64
No
MagicLens: Self-Supervised Image Retrieval with ...
2024-03-28
Code
16
MagicLens (CLIP L)
61.7
No
MagicLens: Self-Supervised Image Retrieval with ...
2024-03-28
Code
17
WeiMoCIR (CLIP L/14)
60.87
No
Training-free Zero-shot Composed Image Retrieval...
2024-09-07
Code
18
WeiMoCIR (CLIP G/14)
60.41
No
Training-free Zero-shot Composed Image Retrieval...
2024-09-07
Code
19
WeiMoCIR (CLIP H/14)
59.76
No
Training-free Zero-shot Composed Image Retrieval...
2024-09-07
Code
20
MTCIR (BLIP B/16)
58.87
No
Pretrain like Your Inference: Masked Tuning Impr...
2023-11-13
Code
21
IP-CIR + LDRE (CLIP L/14)
58.82
No
Imagine and Seek: Improving Composed Image Retri...
2024-11-24
-
22
MagicLens (CLIP B)
58
No
MagicLens: Self-Supervised Image Retrieval with ...
2024-03-28
Code
23
WeiMoCIR (CLIP B/32)
57.69
No
Training-free Zero-shot Composed Image Retrieval...
2024-09-07
Code
24
OSrCIR (CLIP L/14)
57.68
No
Reason-before-Retrieve: One-Stage Reflective Cha...
2024-12-15
Code
25
CompoDiff (CLIP G/14)
57.61
No
CompoDiff: Versatile Composed Image Retrieval Wi...
2023-03-21
Code
26
SEIZE (CLIP B/32)
57.42
No
-
-
Code
27
SEIZE (CLIP L/14)
57.16
No
-
-
Code
28
RTD + LinCIR (CLIP L/14)
56.17
No
An Efficient Post-hoc Framework for Reducing Tas...
2024-06-13
Code
29
iSEARLE (CLIP B/32)
55.69
No
iSEARLE: Improving Textual Inversion for Zero-Sh...
2024-05-05
Code
30
LDRE (CLIP L/14)
55.57
No
-
-
Code
31
iSEARLE-OTI (CLIP B/32)
55.18
No
iSEARLE: Improving Textual Inversion for Zero-Sh...
2024-05-05
Code
32
LDRE (CLIP B/32)
55.13
No
-
-
Code
33
Context-I2W (CLIP L/14)
55.1
No
Context-I2W: Mapping Images to Context-dependent...
2023-09-28
Code
34
MTCIR (CLIP L/14)
54.58
No
Pretrain like Your Inference: Masked Tuning Impr...
2023-11-13
Code
35
OSrCIR (CLIP B/32)
54.54
No
Reason-before-Retrieve: One-Stage Reflective Cha...
2024-12-15
Code
36
CompoDiff (CLIP L/14)
54.36
No
CompoDiff: Versatile Composed Image Retrieval Wi...
2023-03-21
Code
37
iSEARLE-XL-OTI (CLIP L/14)
54.05
No
iSEARLE: Improving Textual Inversion for Zero-Sh...
2024-05-05
Code
38
iSEARLE-XL (CLIP L/14)
54
No
iSEARLE: Improving Textual Inversion for Zero-Sh...
2024-05-05
Code
39
SEARLE
53.42
No
Zero-Shot Composed Image Retrieval with Textual ...
2023-03-27
Code
40
LinCIR (CLIP L/14)
53.25
No
Language-only Efficient Training of Zero-shot Co...
2023-12-04
Code
41
CIReVL (CLIP B/32)
52.51
No
Vision-by-Language for Training-Free Composition...
2023-10-13
Code
42
SEARLE-XL
52.48
No
Zero-Shot Composed Image Retrieval with Textual ...
2023-03-27
Code
43
CIReVL (CLIP L/14)
52.31
No
Vision-by-Language for Training-Free Composition...
2023-10-13
Code
44
Pic2Word
51.7
No
Pic2Word: Mapping Pictures to Words for Zero-sho...
2023-02-06
Code
45
PALAVRA
43.49
No
"This is my unicorn, Fluffy": Personalizing froz...
2022-04-04
Code
#1
CoVR-BLIP-2
SOTA
81.08
R@5
· 2023-08-28
CoVR-2: Automatic Data Construction for Composed Video Retrieval
Code
#2
CoVR-BLIP-2
73.61
R@5
· 2023-08-28
CoVR-2: Automatic Data Construction for Composed Video Retrieval
Code
#3
IP-CIR + LDRE (CLIP G/14)
70.07
R@5
· 2024-11-24
Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy
#4
SEIZE (CLIP G/14)
69.42
R@5
No paper
Code
#5
TransAgg (Laion-CIR-Combined)
SOTA
68.88
R@5
· 2023-06-12
Zero-shot Composed Text-Image Retrieval
Code
#6
ImageScope (CLIP-ViT-L/14)
67.54
R@5
· 2025-03-13
ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning
Code
#7
RTD + LinCIR (CLIP G/14)
67.47
R@5
· 2024-06-13
An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval
Code
#8
OSrCIR (CLIP G/14)
67.25
R@5
· 2024-12-15
Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
Code
#9
MagicLens (CoCa L)
67
R@5
· 2024-03-28
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
Code
#10
LDRE (CLIP G/14)
66.39
R@5
No paper
Code
#11
SPN4CIR (SPN-CC)
65.42
R@5
· 2024-04-17
Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives
Code
#12
LinCIR (CLIP G/14)
64.72
R@5
· 2023-12-04
Language-only Efficient Training of Zero-shot Composed Image Retrieval
Code
#13
SCOT (WACV 2025)
64.34
R@5
· 2025-01-12
SCOT: Self-Supervised Contrastive Pretraining For Zero-Shot Compositional Retrieval
#14
CIReVL (CLIP G/14)
64.29
R@5
· 2023-10-13
Vision-by-Language for Training-Free Compositional Image Retrieval
Code
#15
MagicLens (CoCa B)
64
R@5
· 2024-03-28
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
Code
#16
MagicLens (CLIP L)
61.7
R@5
· 2024-03-28
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
Code
#17
WeiMoCIR (CLIP L/14)
60.87
R@5
· 2024-09-07
Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
Code
#18
WeiMoCIR (CLIP G/14)
60.41
R@5
· 2024-09-07
Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
Code
#19
WeiMoCIR (CLIP H/14)
59.76
R@5
· 2024-09-07
Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
Code
#20
MTCIR (BLIP B/16)
58.87
R@5
· 2023-11-13
Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval
Code
#21
IP-CIR + LDRE (CLIP L/14)
58.82
R@5
· 2024-11-24
Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy
#22
MagicLens (CLIP B)
58
R@5
· 2024-03-28
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
Code
#23
WeiMoCIR (CLIP B/32)
57.69
R@5
· 2024-09-07
Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
Code
#24
OSrCIR (CLIP L/14)
57.68
R@5
· 2024-12-15
Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
Code
#25
CompoDiff (CLIP G/14)
SOTA
57.61
R@5
· 2023-03-21
CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
Code
#26
SEIZE (CLIP B/32)
57.42
R@5
No paper
Code
#27
SEIZE (CLIP L/14)
57.16
R@5
No paper
Code
#28
RTD + LinCIR (CLIP L/14)
56.17
R@5
· 2024-06-13
An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval
Code
#29
iSEARLE (CLIP B/32)
55.69
R@5
· 2024-05-05
iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval
Code
#30
LDRE (CLIP L/14)
55.57
R@5
No paper
Code
#31
iSEARLE-OTI (CLIP B/32)
55.18
R@5
· 2024-05-05
iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval
Code
#32
LDRE (CLIP B/32)
55.13
R@5
No paper
Code
#33
Context-I2W (CLIP L/14)
55.1
R@5
· 2023-09-28
Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval
Code
#34
MTCIR (CLIP L/14)
54.58
R@5
· 2023-11-13
Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval
Code
#35
OSrCIR (CLIP B/32)
54.54
R@5
· 2024-12-15
Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
Code
#36
CompoDiff (CLIP L/14)
54.36
R@5
· 2023-03-21
CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
Code
#37
iSEARLE-XL-OTI (CLIP L/14)
54.05
R@5
· 2024-05-05
iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval
Code
#38
iSEARLE-XL (CLIP L/14)
54
R@5
· 2024-05-05
iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval
Code
#39
SEARLE
53.42
R@5
· 2023-03-27
Zero-Shot Composed Image Retrieval with Textual Inversion
Code
#40
LinCIR (CLIP L/14)
53.25
R@5
· 2023-12-04
Language-only Efficient Training of Zero-shot Composed Image Retrieval
Code
#41
CIReVL (CLIP B/32)
52.51
R@5
· 2023-10-13
Vision-by-Language for Training-Free Compositional Image Retrieval
Code
#42
SEARLE-XL
52.48
R@5
· 2023-03-27
Zero-Shot Composed Image Retrieval with Textual Inversion
Code
#43
CIReVL (CLIP L/14)
52.31
R@5
· 2023-10-13
Vision-by-Language for Training-Free Compositional Image Retrieval
Code
#44
Pic2Word
SOTA
51.7
R@5
· 2023-02-06
Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval
Code
#45
PALAVRA
SOTA
43.49
R@5
· 2022-04-04
"This is my unicorn, Fluffy": Personalizing frozen vision-language representations
Code