papers AI Learner
The Github is limit! Click to go to the new site.

Distance Metric Learned Collaborative Representation Classifier

2019-05-03
Tapabrata Chakraborti, Brendan McCane, Steven Mills, Umapada Pal

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.01168

PDF

http://arxiv.org/pdf/1905.01168


Similar Posts

Comments