Title
Deep Metric Learning and Image Classification with Nearest Neighbour Gaussian Kernels
Abstract
We present a Gaussian kernel loss function and training algorithm for convolutional neural networks that can be directly applied to both distance metric learning and image classification problems. Our method treats all training features from a deep neural network as Gaussian kernel centres and computes loss by summing the influence of a feature's nearby centres in the feature embedding space. Our approach is made scalable by treating it as an approximate nearest neighbour search problem. We show how to make end-to-end learning feasible, resulting in a well formed embedding space, in which semantically related instances are likely to be located near one another, regardless of whether or not the network was trained on those classes. Our approach outperforms state-of-the-art deep metric learning approaches on embedding learning challenges, as well as conventional softmax classification on several datasets.
Year
DOI
Venue
2018
10.1109/ICIP.2018.8451297
2018 25th IEEE International Conference on Image Processing (ICIP)
Keywords
Field
DocType
Metric Learning,Deep Learning,Transfer Learning,Image Classification,Gaussian Kernel
Embedding,Pattern recognition,Softmax function,Convolutional neural network,Computer science,Metric (mathematics),Artificial intelligence,Deep learning,Artificial neural network,Contextual image classification,Gaussian function
Conference
ISSN
ISBN
Citations 
1522-4880
978-1-4799-7062-9
2
PageRank 
References 
Authors
0.37
0
3
Name
Order
Citations
PageRank
Benjamin J. Meyer132.41
Ben Harwood283.16
Tom Drummond32676159.45