Graph Convolutional Networks for Learning with Few Clean and many Noisy Labels - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

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

(1) , (2) , (1) , (2) , (3)
1
2
3

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 learning to discriminate clean from noisy examples using a weighted binary cross-entropy loss function, and then the GCN-inferred "clean" probability is 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 GCN-based cleaning process significantly improves the classification accuracy over not cleaning the noisy data and standard few-shot classification where only few clean examples are used. The proposed GCN-based method outperforms the transductive approach (Douze et al., 2018) that is using the same additional data without labels.
Fichier principal
Vignette du fichier
1910.00324.pdf (1.86 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02370212 , version 1 (19-11-2019)

Identifiers

Cite

Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondřej Chum, Cordelia Schmid. Graph Convolutional Networks for Learning with Few Clean and many Noisy Labels. 2019. ⟨hal-02370212⟩
120 View
372 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More