Print Email Facebook Twitter Multi-Label Gold Asymmetric Loss Correction with Single-Label Regulators Title Multi-Label Gold Asymmetric Loss Correction with Single-Label Regulators Author Pene, Cosmin (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 an emerging extension of the multi-class classification where an image contains multiple labels. Not only acquiring a clean and fully labeled dataset in multi-label learning is extremely expensive, but also many of the actual labels are corrupted or missing due to the automated or non-expert annotation techniques. Noisy label data decrease the prediction performance drastically. In this paper, we propose a novel Gold Asymmetric Loss Correction with Single-Label Regulators (GALC-SLR) that operates robust against noisy labels. GALC-SLR estimates the noise confusion matrix using single-label samples, then constructs an asymmetric loss correction via estimated confusion matrix to avoid overfitting to the noisy labels. Empirical results show that our method outperforms the state-of-the-art original asymmetric loss multi-label classifier under all corruption levels, showing mean average precision improvement up to 28.67\% on a real-world dataset of MS-COCO, yielding a better generalization of the unseen data and increased prediction performance. Subject Multi-label classificationLabel NoiseRobust learningDeep Neural NetworksNoise estimationAsymmetric Loss To reference this document use: http://resolver.tudelft.nl/uuid:b42c6372-ea80-4b1a-b3ee-fa00f4ad8998 Part of collection Student theses Document type bachelor thesis Rights © 2021 Cosmin Pene Files PDF Multi_Label_Gold_Asymmetr ... STLAST.pdf 3.16 MB Close viewer /islandora/object/uuid:b42c6372-ea80-4b1a-b3ee-fa00f4ad8998/datastream/OBJ/view