Skip to Main content Skip to Navigation
New interface
Conference papers

Graph Convolutional Networks for Learning with Few Clean and Many Noisy Labels

Abstract : In this work we consider the problem of learning a classifier from noisy labels when a few clean labeled examples are given. The structure of clean and noisy data is modeled by a graph per class and Graph Convolutional Networks (GCN) are used to predict class relevance of noisy examples. For each class, the GCN is treated as a binary classifier, which learns to discriminate clean from noisy examples using a weighted binary cross-entropy loss function. The GCN-inferred "clean" probability is then exploited as a relevance measure. Each noisy example is weighted by its relevance when learning a classifier for the end task. We evaluate our method on an extended version of a few-shot learning problem, where the few clean examples of novel classes are supplemented with additional noisy data. Experimental results show that our GCNbased cleaning process significantly improves the classification accuracy over not cleaning the noisy data, as well as standard few-shot classification where only few clean examples are used.
Document type :
Conference papers
Complete list of metadata
Contributor : Yannis Avrithis Connect in order to contact the contributor
Submitted on : Tuesday, December 8, 2020 - 9:15:18 PM
Last modification on : Friday, November 18, 2022 - 9:24:26 AM
Long-term archiving on: : Tuesday, March 9, 2021 - 8:14:40 PM


Files produced by the author(s)



Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondřej Chum, Cordelia Schmid. Graph Convolutional Networks for Learning with Few Clean and Many Noisy Labels. ECCV 2020 - 16th European Conference on Computer Vision, Aug 2020, Virtual, United Kingdom. pp.286-302, ⟨10.1007/978-3-030-58607-2_17⟩. ⟨hal-03047513⟩



Record views


Files downloads