Print Email Facebook Twitter Robust multi-label learning for weakly labeled data Title Robust multi-label learning for weakly labeled data Author Marinov, Atanas (TU Delft Electrical Engineering, Mathematics and Computer Science; TU Delft Software Technology) Contributor Chen, Lydia Y. (mentor) Ghiassi, S. (mentor) Younesian, T. (mentor) Kuipers, F.A. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2021-07-02 Abstract Multi-label learning is one of the hot problems in the field of machine learning. The deep neural networks used to solve it could be quite complex and have a huge capacity. This enormous capacity, however, could also be a negative, as they tend to eventually overfit the undesirable features of the data. One such feature presented in the real-world datasets is imperfect labels. A particularly common type of label imperfection is called weak labels. This corruption is characterized not only by the presence of all relevant labels but also by the addition of some irrelevant ones. In this paper, a novel method, Co-ASL, is introduced to deal with the label noise in multi-label datasets. It combines the state-of-the-art approach for multi-label learning, ASL, with the famous robust training strategy, Co-teaching. The performance of the method is then evaluated on noisy versions of MS-COCO to show the lack of overfitting and the performance improvement over the non-robust multi-label ASL. Subject Multi-label classificationRobust learningWeak labelsDeep learning To reference this document use: http://resolver.tudelft.nl/uuid:f9b7b445-2ffd-43be-8e5b-3ed852b1c784 Part of collection Student theses Document type bachelor thesis Rights © 2021 Atanas Marinov Files PDF Robust_multi_label_learni ... d_data.pdf 518.83 KB Close viewer /islandora/object/uuid:f9b7b445-2ffd-43be-8e5b-3ed852b1c784/datastream/OBJ/view