# Distance Metric Learned Collaborative Representation Classifier

## TL;DR

This paper introduces DML-CRC, a method that learns an optimal Mahalanobis distance metric within a deep network to improve fine-grained classification accuracy, achieving state-of-the-art results.

## Contribution

It proposes a novel end-to-end approach to learn a Mahalanobis distance metric integrated with a convolutional network for enhanced classification.

## Key findings

- State-of-the-art accuracy on CUB Birds, Oxford Flowers, Oxford-IIIT Pets datasets.
- Network-agnostic method applicable to various classification tasks.
- Effective integration of metric learning with deep feature extraction.

## Abstract

Any generic deep machine learning algorithm is essentially a function fitting exercise, where the network tunes its weights and parameters to learn discriminatory features by minimizing some cost function. Though the network tries to learn the optimal feature space, it seldom tries to learn an optimal distance metric in the cost function, and hence misses out on an additional layer of abstraction. We present a simple effective way of achieving this by learning a generic Mahalanabis distance in a collaborative loss function in an end-to-end fashion with any standard convolutional network as the feature learner. The proposed method DML-CRC gives state-of-the-art performance on benchmark fine-grained classification datasets CUB Birds, Oxford Flowers and Oxford-IIIT Pets using the VGG-19 deep network. The method is network agnostic and can be used for any similar classification tasks.