HyperAI
الرئيسيةالأخبارأحدث الأوراق البحثيةالدروسمجموعات البياناتالموسوعةSOTAنماذج LLMلوحة الأداء GPUالفعاليات
البحث
حول
HyperAI

Zero Shot Composed Image Retrieval Zs Cir On 1

المقاييس

R@5

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج
R@5
Paper TitleRepository
LDRE (CLIP L/14)55.57LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval
CIReVL (CLIP G/14)64.29Vision-by-Language for Training-Free Compositional Image Retrieval
CoVR-BLIP-273.61CoVR-2: Automatic Data Construction for Composed Video Retrieval
SEIZE (CLIP G/14)69.42Semantic Editing Increment Benefits Zero-Shot Composed Image Retrieval
OSrCIR (CLIP L/14)57.68Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
WeiMoCIR (CLIP G/14)60.41Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
iSEARLE-XL-OTI (CLIP L/14)54.05iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval
iSEARLE-OTI (CLIP B/32)55.18iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval
CompoDiff (CLIP G/14)57.61CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
SEIZE (CLIP B/32)57.42Semantic Editing Increment Benefits Zero-Shot Composed Image Retrieval
WeiMoCIR (CLIP B/32)57.69Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
OSrCIR (CLIP G/14)67.25Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
MTCIR (CLIP L/14)54.58Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval-
MagicLens (CLIP B)58.0MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
LDRE (CLIP G/14)66.39LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval
MagicLens (CoCa B)64.0MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
LinCIR (CLIP G/14)64.72Language-only Efficient Training of Zero-shot Composed Image Retrieval
ImageScope (CLIP-ViT-L/14)67.54ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning-
LDRE (CLIP B/32)55.13LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval
CIReVL (CLIP B/32)52.51Vision-by-Language for Training-Free Compositional Image Retrieval
0 of 46 row(s) selected.