HyperAIHyperAI

Image Retrieval On Cirr

Metrics

(Recall@5+Recall_subset@1)/2

Results

Performance results of various models on this benchmark

Model Name
(Recall@5+Recall_subset@1)/2
Paper TitleRepository
TG-CIR (Wen et al., 2023)75.6Target-Guided Composed Image Retrieval-
SPRC282.66Sentence-level Prompts Benefit Composed Image Retrieval-
SPN4CIR82.69Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives-
MMRet-MLLM-MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval-
CASE (Pre-trained on LaSCo.Ca)78.25Data Roaming and Quality Assessment for Composed Image Retrieval-
SPRC81.39Sentence-level Prompts Benefit Composed Image Retrieval-
CLIP4Cir (v2)69.09Conditioned and Composed Image Retrieval Combining and Partially Fine-Tuning CLIP-Based Features
CaLa78.74CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval-
CASE77.5Data Roaming and Quality Assessment for Composed Image Retrieval-
CLIP4Cir (v3)75.10Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features-
CLIP4Cir63.87Effective Conditioned and Composed Image Retrieval Combining CLIP-Based Features
BLIP4CIR+Bi72.59Bi-directional Training for Composed Image Retrieval via Text Prompt Learning-
Candidate Set Re-ranking80.9Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder-
VISTA (base)75.9VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval-
CIRPLANT45.88Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models-
SPN4CIR (SPRC)82.69Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives-
ARTEMIS43.05ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity-
0 of 17 row(s) selected.
Image Retrieval On Cirr | SOTA | HyperAI