toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
   print
  Record Links
Author (up) Diego Velazquez; Pau Rodriguez; Josep M. Gonfaus; Xavier Roca; Jordi Gonzalez edit  url
openurl 
  Title A Closer Look at Embedding Propagation for Manifold Smoothing Type Journal Article
  Year 2022 Publication Journal of Machine Learning Research Abbreviated Journal JMLR  
  Volume 23 Issue 252 Pages 1-27  
  Keywords Regularization; emi-supervised learning; self-supervised learning; adversarial robustness; few-shot classification  
  Abstract Supervised training of neural networks requires a large amount of manually annotated data and the resulting networks tend to be sensitive to out-of-distribution (OOD) data.
Self- and semi-supervised training schemes reduce the amount of annotated data required during the training process. However, OOD generalization remains a major challenge for most methods. Strategies that promote smoother decision boundaries play an important role in out-of-distribution generalization. For example, embedding propagation (EP) for manifold smoothing has recently shown to considerably improve the OOD performance for few-shot classification. EP achieves smoother class manifolds by building a graph from sample embeddings and propagating information through the nodes in an unsupervised manner. In this work, we extend the original EP paper providing additional evidence and experiments showing that it attains smoother class embedding manifolds and improves results in settings beyond few-shot classification. Concretely, we show that EP improves the robustness of neural networks against multiple adversarial attacks as well as semi- and
self-supervised learning performance.
 
  Address 9/2022  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number Admin @ si @ VRG2022 Serial 3762  
Permanent link to this record
Select All    Deselect All
 |   | 
Details
   print

Save Citations:
Export Records: