Metric Learning on In-Shop

Metric: R@1 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide augmentations

Sort:

#	Model↕	R@1▼	Augmentations	Paper	Date↕	Code
1	Unicom+ViT-L@336px	96.7	Yes	Unicom: Universal and Compact Representation Lea...	2023-04-12	Code
2	STIR	95	No	STIR: Siamese Transformer for Image Retrieval Po...	2023-04-26	Code
3	MGA	94.3	No	Fashion Image Retrieval with Multi-Granular Alig...	2023-02-16	-
4	Hyp-ViT	92.5	Yes	Hyperbolic Vision Transformers: Combining Improv...	2022-03-21	Code
5	Hyp-DINO	92.4	No	Hyperbolic Vision Transformers: Combining Improv...	2022-03-21	Code
6	CCL (ResNet-50)	92.31	No	Center Contrastive Loss for Metric Learning	2023-08-01	-
7	Gradient Surgery	92.21	No	Dissecting the impact of different loss function...	2022-01-27	-
8	ResNet-50 + Metrix	92.2	Yes	It Takes Two to Tango: Mixup for Deep Metric Lea...	2021-06-09	Code
9	ViT-Triplet	92.1	No	STIR: Siamese Transformer for Image Retrieval Po...	2023-04-26	Code
10	EfficientDML-VPTSP-G/512	92.1	Yes	Learning Semantic Proxies from Visual Prompts fo...	2024-02-04	Code
11	NED	91.3	Yes	Calibrated neighborhood aware confidence measure...	2020-06-08	-
12	ResNet-50 + ProxyNCA++	90.9	Yes	ProxyNCA++: Revisiting and Revitalizing Proxy Ne...	2020-04-02	Code
13	ResNet-50 + Cross-Entropy	90.6	Yes	A unifying mutual information view of metric lea...	2020-03-19	Code
14	SCT(512)	90	No	Hard negative examples are hard, but useful	2020-07-24	Code
15	EPSHN(512)	87.8	No	Improved Embeddings with Easy Positive Triplet M...	2019-04-08	Code

#1Unicom+ViT-L@336pxSOTA
96.7
R@1· Augmentations· 2023-04-12
Unicom: Universal and Compact Representation Learning for Image Retrieval Code
#2STIR
95
R@1· 2023-04-26
STIR: Siamese Transformer for Image Retrieval Postprocessing Code
#3MGASOTA
94.3
R@1· 2023-02-16
Fashion Image Retrieval with Multi-Granular Alignment
#4Hyp-ViTSOTA
92.5
R@1· Augmentations· 2022-03-21
Hyperbolic Vision Transformers: Combining Improvements in Metric Learning Code
#5Hyp-DINO
92.4
R@1· 2022-03-21
Hyperbolic Vision Transformers: Combining Improvements in Metric Learning Code
#6CCL (ResNet-50)
92.31
R@1· 2023-08-01
Center Contrastive Loss for Metric Learning
#7Gradient SurgerySOTA
92.21
R@1· 2022-01-27
Dissecting the impact of different loss functions with gradient surgery
#8ResNet-50 + MetrixSOTA
92.2
R@1· Augmentations· 2021-06-09
It Takes Two to Tango: Mixup for Deep Metric Learning Code
#9ViT-Triplet
92.1
R@1· 2023-04-26
STIR: Siamese Transformer for Image Retrieval Postprocessing Code
#10EfficientDML-VPTSP-G/512
92.1
R@1· Augmentations· 2024-02-04
Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning Code
#11NEDSOTA
91.3
R@1· Augmentations· 2020-06-08
Calibrated neighborhood aware confidence measure for deep metric learning
#12ResNet-50 + ProxyNCA++SOTA
90.9
R@1· Augmentations· 2020-04-02
ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis Code
#13ResNet-50 + Cross-EntropySOTA
90.6
R@1· Augmentations· 2020-03-19
A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses Code
#14SCT(512)
90
R@1· 2020-07-24
Hard negative examples are hard, but useful Code
#15EPSHN(512)SOTA
87.8
R@1· 2019-04-08
Improved Embeddings with Easy Positive Triplet Mining Code