HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Image Retrieval On Fashion Iq

Metrics

(Recall@10+Recall@50)/2
Recall@10

Results

Performance results of various models on this benchmark

Paper Title
SPN4CIR (SPRC)66.4156.37Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives
SPN4CIR66.41-Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives
SPRC64.8554.92Sentence-level Prompts Benefit Composed Image Retrieval
Candidate Set Re-ranking62.1551.17Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder
RUTIR (BLIP B/16)61.32-Ranking-aware Uncertainty for Text-guided Image Retrieval
CASE59.7348.79Data Roaming and Quality Assessment for Composed Image Retrieval
CaLa57.9646.69CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval
BLIP4CIR+Bi55.4-Bi-directional Training for Composed Image Retrieval via Text Prompt Learning
CLIP4Cir (v3)55.36-Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features
RUTIR (CLIP ResNet50)55.27-Ranking-aware Uncertainty for Text-guided Image Retrieval
Css-Net51.34-Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations
MUR (4*ResNet50)50.61-Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization
CLIP4Cir (v2)50.03-Conditioned and Composed Image Retrieval Combining and Partially Fine-Tuning CLIP-Based Features
MUR47.28-Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization
CLIP4Cir47.21-Effective Conditioned and Composed Image Retrieval Combining CLIP-Based Features
MMRet-MLLM46.135.6MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval
RTIC-GCN40.64-RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Network
CoSMo39.45-CoSMo: Content-Style Modulation for Image Retrieval With Text Feedback
CurlingNet38.45-CurlingNet: Compositional Learning between Images and Text for Fashion IQ Data
VAL w/ GloVe35.38-Image Search With Text Feedback by Visiolinguistic Attention Learning
0 of 21 row(s) selected.