HyperAI超神经

Image Retrieval On Cars196

评估指标

R@1

评测结果

各个模型在此基准测试上的表现结果

		Paper Title
CGD (MG/SG)	94.8	Combination of Multiple Global Descriptors for Image Retrieval
ProxyNCA++	90.1	ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis
NormSoftmax2048 (ResNet-50)	89.3	Classification is a Strong Baseline for Deep Metric Learning
MES-Loss	87.89	MES-Loss: Mutually equidistant separation metric learning loss function
Margin	86.9	Sampling Matters in Deep Embedding Learning
MS512	84.1	Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning
EPSHN512	82.7	Improved Embeddings with Easy Positive Triplet Mining
HTL	81.4	Deep Metric Learning with Hierarchical Triplet Loss

0 of 8 row(s) selected.

Image Retrieval On Cars196 | SOTA | HyperAI超神经