Deep metric learning and image classification with nearest neighbour gaussian kernels

Benjamin J. Meyer, Ben Harwood, Tom Drummond

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

5 Citations (Scopus)


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.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Image Processing - Proceedings
EditorsNikolaos Boulgouris, Lisimachos P. Kondi
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages5
ISBN (Electronic)9781479970612
ISBN (Print)9781479970629
Publication statusPublished - 2018
EventIEEE International Conference on Image Processing 2018 - Athens, Greece
Duration: 7 Oct 201810 Oct 2018
Conference number: 25th (Proceedings)


ConferenceIEEE International Conference on Image Processing 2018
Abbreviated titleICIP 2018
Internet address


  • Deep Learning
  • Gaussian Kernel
  • Image Classification
  • Metric Learning
  • Transfer Learning

Cite this