Metric Learning On Cars196

Metrics

R@1

Results

Performance results of various models on this benchmark

Model Name	R@1	Paper Title	Repository
Gradient Surgery	86.5	Dissecting the impact of different loss functions with gradient surgery	-
Hyp-DINO	89.2	Hyperbolic Vision Transformers: Combining Improvements in Metric Learning
Hyp-ViT	86.5	Hyperbolic Vision Transformers: Combining Improvements in Metric Learning
BN-Inception + Proxy-Anchor	88.3	Proxy Anchor Loss for Deep Metric Learning
Margin + DAS	88.34	DAS: Densely-Anchored Sampling for Deep Metric Learning
Group Loss	85.6	The Group Loss for Deep Metric Learning
ABE-8-512	85.2	Attention-based Ensemble for Deep Metric Learning	-
ResNet50 (128) + PADS	83.5	PADS: Policy-Adapted Sampling for Visual Similarity Learning
MS + SEC + DAS	87.8	DAS: Densely-Anchored Sampling for Deep Metric Learning
SCT(64)	73.2	Hard negative examples are hard, but useful
ProxyAnchor + DIML	87.01	Towards Interpretable Deep Metric Learning with Structural Matching
ResNet-50 + Intra-Batch	88.1	Learning Intra-Batch Connections for Deep Metric Learning
EfficientDML-VPTSP-G/512	91.2	Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning
EPSHN(512)	82.7	Improved Embeddings with Easy Positive Triplet Mining
NED	91.5	Calibrated neighborhood aware confidence measure for deep metric learning	-
ResNet-50 + Margin	79.6	Sampling Matters in Deep Embedding Learning
Recall@k Surrogate loss (ResNet-50)	88.3	Recall@k Surrogate Loss with Large Batches and Similarity Mixup
ABE + HORDE	88.0	Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings
ResNet-50 + Metrix	89.6	It Takes Two to Tango: Mixup for Deep Metric Learning
Recall@k Surrogate loss (ViT-B/16)	89.5	Recall@k Surrogate Loss with Large Batches and Similarity Mixup

0 of 36 row(s) selected.