Skip to Main content Skip to Navigation
New interface
Conference papers

Multiple Instance Learning for Training Neural Networks under Label Noise

Stefan Duffner 1 Christophe Garcia 1 
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : In this paper, we present an extensive study of different neural network-based approaches and loss functions applied to the Multiple Instance Learning (MIL) problem and binary classification. In the MIL setting, training is performed on small sets of instances called bags, where each positive bag contains at least one positive instance and each negative bag contains only negative instances. We propose a new loss function based on the generalised mean and an effective training strategy particularly suited to this setting and to problems where the instances of one class contain a considerable amount of label noise. Furthermore, we present a probabilistic approach to dynamically estimate the label noise in this unbalanced binary classification setting and utilise it to automatically modulate the hyper-parameter of our proposed loss function. We experimentally evaluated our approach on a number of standard benchmarks for binary classification and showed that it outperforms standard neural network optimisation algorithms as well as most state-of-the-art MIL methods, both on numerical/categorical vector data with MLP architectures and images with Convolutional Neural Networks.
Complete list of metadata

Cited literature [37 references]  Display  Hide  Download
Contributor : Stefan Duffner Connect in order to contact the contributor
Submitted on : Monday, July 20, 2020 - 9:44:13 AM
Last modification on : Friday, September 30, 2022 - 11:34:16 AM
Long-term archiving on: : Tuesday, December 1, 2020 - 1:10:06 AM


Files produced by the author(s)



Stefan Duffner, Christophe Garcia. Multiple Instance Learning for Training Neural Networks under Label Noise. International Joint Conference on Neural Networks (IJCNN), Jul 2020, Glasgow, United Kingdom. ⟨10.1109/IJCNN48605.2020.9206669⟩. ⟨hal-02902571⟩



Record views


Files downloads