Check the preview of 2nd version of this platform being developed by the open MLCommons taskforce on automation and reproducibility as a free, open-source and technology-agnostic on-prem platform.

Squared Earth Mover's Distance-based Loss for Training Deep Neural Networks

lib:28d9d661a3b4a38b (v1.0.0)

Vote to reproduce this paper and share portable workflows   1 
Authors: Le Hou,Chen-Ping Yu,Dimitris Samaras
ArXiv: 1611.05916
Document:  PDF  DOI 
Artifact development version: GitHub
Abstract URL: http://arxiv.org/abs/1611.05916v4


In the context of single-label classification, despite the huge success of deep learning, the commonly used cross-entropy loss function ignores the intricate inter-class relationships that often exist in real-life tasks such as age classification. In this work, we propose to leverage these relationships between classes by training deep nets with the exact squared Earth Mover's Distance (also known as Wasserstein distance) for single-label classification. The squared EMD loss uses the predicted probabilities of all classes and penalizes the miss-predictions according to a ground distance matrix that quantifies the dissimilarities between classes. We demonstrate that on datasets with strong inter-class relationships such as an ordering between classes, our exact squared EMD losses yield new state-of-the-art results. Furthermore, we propose a method to automatically learn this matrix using the CNN's own features during training. We show that our method can learn a ground distance matrix efficiently with no inter-class relationship priors and yield the same performance gain. Finally, we show that our method can be generalized to applications that lack strong inter-class relationships and still maintain state-of-the-art performance. Therefore, with limited computational overhead, one can always deploy the proposed loss function on any dataset over the conventional cross-entropy.

Relevant initiatives  

Related knowledge about this paper Reproduced results (crowd-benchmarking and competitions) Artifact and reproducibility checklists Common formats for research projects and shared artifacts Reproducibility initiatives

Comments  

Please log in to add your comments!
If you notice any inapropriate content that should not be here, please report us as soon as possible and we will try to remove it within 48 hours!