Metric Learning On Stanford Online Products 1

Métriques

R@1

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	R@1	Paper Title
ViT-Triplet	86.5	STIR: Siamese Transformer for Image Retrieval Postprocessing
EPSHN(512)	78.3	Improved Embeddings with Easy Positive Triplet Mining
Hyp-DINO	85.1	Hyperbolic Vision Transformers: Combining Improvements in Metric Learning
ResNet50 + NIR	80.7	Non-isotropy Regularization for Proxy-based Deep Metric Learning
ResNet-50 + Cross-Entropy	81.1	A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses
HAPPIER_F	81.8	Hierarchical Average Precision Training for Pertinent Image Retrieval
QB-Norm+RDML	78.1	Cross Modal Retrieval with Querybank Normalisation
Group Loss	75.7	The Group Loss for Deep Metric Learning
ROADMAP (ResNet-50)	83.1	Robust and Decomposable Average Precision for Image Retrieval
Margin + DIML	79.26	Towards Interpretable Deep Metric Learning with Structural Matching
ResNet50 + S2SD	81.0	S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning
Recall@k Surrogate Loss (ViT-B/16)	88.0	Recall@k Surrogate Loss with Large Batches and Similarity Mixup
Unicom+ViT-L@336px	91.2	Unicom: Universal and Compact Representation Learning for Image Retrieval
Recall@k Surrogate Loss (ResNet-50)	82.7	Recall@k Surrogate Loss with Large Batches and Similarity Mixup
BN-Inception + Proxy-Anchor	80.3	Proxy Anchor Loss for Deep Metric Learning
ResNet50 (128) + PADS	76.5	PADS: Policy-Adapted Sampling for Visual Similarity Learning
Recall@k Surrogate Loss (ViT-B/32)	85.1	Recall@k Surrogate Loss with Large Batches and Similarity Mixup
STIR	88.3	STIR: Siamese Transformer for Image Retrieval Postprocessing
ResNet50 (128) + MIC	77.2	MIC: Mining Interclass Characteristics for Improved Metric Learning
ResNet50 + Language	81.3	Integrating Language Guidance into Vision-based Deep Metric Learning

0 of 33 row(s) selected.