Zero Shot Composed Image Retrieval Zs Cir On 1

Métriques

R@5

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	R@5	Paper Title	Repository
LDRE (CLIP L/14)	55.57	LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval
CIReVL (CLIP G/14)	64.29	Vision-by-Language for Training-Free Compositional Image Retrieval
CoVR-BLIP-2	73.61	CoVR-2: Automatic Data Construction for Composed Video Retrieval
SEIZE (CLIP G/14)	69.42	Semantic Editing Increment Benefits Zero-Shot Composed Image Retrieval
OSrCIR (CLIP L/14)	57.68	Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
WeiMoCIR (CLIP G/14)	60.41	Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
iSEARLE-XL-OTI (CLIP L/14)	54.05	iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval
iSEARLE-OTI (CLIP B/32)	55.18	iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval
CompoDiff (CLIP G/14)	57.61	CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
SEIZE (CLIP B/32)	57.42	Semantic Editing Increment Benefits Zero-Shot Composed Image Retrieval
WeiMoCIR (CLIP B/32)	57.69	Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
OSrCIR (CLIP G/14)	67.25	Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
MTCIR (CLIP L/14)	54.58	Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval	-
MagicLens (CLIP B)	58.0	MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
LDRE (CLIP G/14)	66.39	LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval
MagicLens (CoCa B)	64.0	MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
LinCIR (CLIP G/14)	64.72	Language-only Efficient Training of Zero-shot Composed Image Retrieval
ImageScope (CLIP-ViT-L/14)	67.54	ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning	-
LDRE (CLIP B/32)	55.13	LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval
CIReVL (CLIP B/32)	52.51	Vision-by-Language for Training-Free Compositional Image Retrieval

0 of 46 row(s) selected.