TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	EXTRA DATA	REMOVE
Metric Learning	CARS196	ABE + HORDE	R@1	88.0	# 19
Metric Learning	CUB-200-2011	ABE + HORDE	R@1	66.8	# 18

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/metric-learning-with-horde-high-order/metric-learning-on-cub-200-2011)](https://paperswithcode.com/sota/metric-learning-on-cub-200-2011?p=metric-learning-with-horde-high-order)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/metric-learning-with-horde-high-order/metric-learning-on-cars196)](https://paperswithcode.com/sota/metric-learning-on-cars196?p=metric-learning-with-horde-high-order)`

Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings

ICCV 2019 · Pierre Jacob, David Picard, Aymeric Histace, Edouard Klein ·

Learning an effective similarity measure between image representations is key to the success of recent advances in visual search tasks (e.g. verification or zero-shot learning). Although the metric learning part is well addressed, this metric is usually computed over the average of the extracted deep features. This representation is then trained to be discriminative. However, these deep features tend to be scattered across the feature space. Consequently, the representations are not robust to outliers, object occlusions, background variations, etc. In this paper, we tackle this scattering problem with a distribution-aware regularization named HORDE. This regularizer enforces visually-close images to have deep features with the same distribution which are well localized in the feature space. We provide a theoretical analysis supporting this regularization effect. We also show the effectiveness of our approach by obtaining state-of-the-art results on 4 well-known datasets (Cub-200-2011, Cars-196, Stanford Online Products and Inshop Clothes Retrieval).