| MMRet-MLLM |
- mAP@10
- 43.4
|
MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval 2024-12-19 |
코드 1 |
| MMRet-Large (CLIP L/14) |
- mAP@10
- 40.2
|
MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval 2024-12-19 |
코드 1 |
| SCOT (WACV 2025) |
- mAP@10
- 37.88
|
SCOT: Self-Supervised Contrastive Pretraining For Zero-Shot Compositional Retrieval 2025-01-12 |
연결 없음 |
| SEIZE (CLIP G/14 & GPT-4o) |
- mAP@10
- 37.23
|
Semantic Editing Increment Benefits Zero-Shot Composed Image Retrieval 2024-10-28 |
코드 1 · 코드 2 |
| MagicLens (CoCa L) |
- mAP@10
- 35.4
|
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions 2024-03-28 |
코드 1 |
| MMRet-Base (CLIP B/16) |
- mAP@10
- 35.0
|
MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval 2024-12-19 |
코드 1 |
| IP-CIR + LDRE (CLIP G/14) |
- mAP@10
- 34.26
|
Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy 2024-11-24 |
연결 없음 |
| SEIZE (CLIP G/14) |
- mAP@10
- 33.77
|
Semantic Editing Increment Benefits Zero-Shot Composed Image Retrieval 2024-10-28 |
코드 1 · 코드 2 |
| LDRE (CLIP G/14) |
- mAP@10
- 32.24
|
LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval 2024-07-11 |
코드 1 · 코드 2 |
| MagicLens (CoCa B) |
- mAP@10
- 32.0
|
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions 2024-03-28 |
코드 1 |
| OSrCIR (CLIP G/14) |
- mAP@10
- 31.14
|
Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval 2024-12-15 |
코드 1 |
| MagicLens (CLIP L) |
- mAP@10
- 30.8
|
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions 2024-03-28 |
코드 1 |
| CoVR-BLIP-2 |
- mAP@10
- 29.55
|
CoVR-2: Automatic Data Construction for Composed Video Retrieval 2023-08-28 |
코드 1 |
| ImageScope (CLIP-ViT-L/14) |
- mAP@10
- 29.23
- MAP@5
- 28.36
- mAP@50
- 31.88
- mAP@25
- 30.81
|
ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning 2025-03-13 |
코드 1 |
| CIReVL (CLIP G/14) |
- mAP@10
- 27.59
|
Vision-by-Language for Training-Free Compositional Image Retrieval 2023-10-13 |
코드 1 |
| IP-CIR + LDRE (CLIP L/14) |
- mAP@10
- 27.41
|
Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy 2024-11-24 |
연결 없음 |
| SEIZE (CLIP L/14) |
- mAP@10
- 25.82
|
Semantic Editing Increment Benefits Zero-Shot Composed Image Retrieval 2024-10-28 |
코드 1 · 코드 2 |
| OSrCIR (CLIP L/14) |
- mAP@10
- 25.33
|
Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval 2024-12-15 |
코드 1 |
| LDRE (CLIP L/14) |
- mAP@10
- 24.03
|
LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval 2024-07-11 |
코드 1 · 코드 2 |
| MagicLens (CLIP B) |
- mAP@10
- 23.8
|
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions 2024-03-28 |
코드 1 |
| RTD + LinCIR (CLIP G/14) |
- mAP@10
- 22.29
|
An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval 2024-06-13 |
코드 1 |
| LinCIR (CLIP G/14) |
- mAP@10
- 21.01
|
Language-only Efficient Training of Zero-shot Composed Image Retrieval 2023-12-04 |
코드 1 |
| CoLLM (Pretrained - CLIP-L/14) |
- mAP@10
- 20.8
- MAP@5
- 20.3
- mAP@50
- 23.4
|
CoLLM: A Large Language Model for Composed Image Retrieval 2025-03-25 |
코드 1 |
| CoLLM (Pretrained - BLIP-L/16) |
- mAP@10
- 20.4
- MAP@5
- 19.7
- mAP@50
- 23.1
|
CoLLM: A Large Language Model for Composed Image Retrieval 2025-03-25 |
코드 1 |
| OSrCIR (CLIP B/32) |
- mAP@10
- 19.17
|
Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval 2024-12-15 |
코드 1 |
| CIReVL (CLIP L/14) |
- mAP@10
- 19.01
|
Vision-by-Language for Training-Free Compositional Image Retrieval 2023-10-13 |
코드 1 |
| LDRE (CLIP B/32) |
- mAP@10
- 18.32
|
LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval 2024-07-11 |
코드 1 · 코드 2 |
| RTD + LinCIR (CLIP L/14) |
- mAP@10
- 18.11
|
An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval 2024-06-13 |
코드 1 |
| CompoDiff (CLIP G/14) |
- mAP@10
- 17.71
|
CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion 2023-03-21 |
코드 1 |
| CIReVL (CLIP B/32) |
- mAP@10
- 15.42
|
Vision-by-Language for Training-Free Compositional Image Retrieval 2023-10-13 |
코드 1 |