HyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAI超神经

Zero Shot Composed Image Retrieval Zs Cir On 2

评估指标

(Recall@10+Recall@50)/2

评测结果

各个模型在此基准测试上的表现结果

模型名称
(Recall@10+Recall@50)/2
Paper TitleRepository
RTD + LinCIR (CLIP G/14)56.74Reducing Task Discrepancy of Text Encoders for Zero-Shot Composed Image Retrieval
WeiMoCIR (CLIP G/14)47.16Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
SEARLE (CLIP B/32)32.71Zero-Shot Composed Image Retrieval with Textual Inversion
SEARLE-XL-OTI (CLIP L/14)37.76Zero-Shot Composed Image Retrieval with Textual Inversion
LinCIR (CLIP G/14)55.40Language-only Efficient Training of Zero-shot Composed Image Retrieval
iSEARLE-XL (CLIP L/14)38.24iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval
CompoDiff (CLIP G/14)45.37CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
SEARLE-XL (CLIP L/14)35.90Zero-Shot Composed Image Retrieval with Textual Inversion
Context-I2W (CLIP L/14)38.35Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval
WeiMoCIR (CLIP H/14)44.58Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
MagicLens (CoCa B)45.3MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
WeiMoCIR (CLIP L/14)41.27Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
WeiMoCIR (CLIP B/32)39.84Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
MagicLens (CoCa L)48.1MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
CIReVL (CLIP L/14)38.56Vision-by-Language for Training-Free Compositional Image Retrieval
CoLLM (Pretrained - CLIP-L/14)39.8--
OSrCIR (CLIP B/32)42.87Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
PALAVRA28.51"This is my unicorn, Fluffy": Personalizing frozen vision-language representations
CoVR-BLIP-248.3CoVR-2: Automatic Data Construction for Composed Video Retrieval
OSrCIR (CLIP G/14)47.34Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
0 of 40 row(s) selected.