Journal
IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM
Volume -, Issue -, Pages 525-528Publisher
IEEE
DOI: 10.1109/IGARSS39084.2020.9324069
Keywords
noisy labels; regularization; label correlations; multi-label classification; deep neural networks
Categories
Funding
- China Scholarship Council
- Helmholtz Association (SiPEO) [VH-NG-1018]
- European Research Council (ERC) [ERC-2016-StG-714087]
Ask authors/readers for more resources
Training deep neural networks requires well-annotated datasets. However, real world datasets are often noisy, especially in a multi-label scenario, i.e. where each data point can be attributed to more than one class. To this end, we propose a regularization method to learn multi-label classification networks from noisy data. This regularization is based on the assumption that semantically close classes are more likely to appear together in a given image. Hereby, we encode label correlations with prior knowledge and regularize noisy network predictions using label correlations. To evaluate its effectiveness, we perform experiments on a mutli-label aerial image dataset contaminated with controlled levels of label noise. Results indicate that networks trained using the proposed method outperform those directly learned from noisy labels and that the benefits increase proportionally to the amount of noise present.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available