Print Email Facebook Twitter Classifying Continuous Labels: A Simple Tweak to Make Regression Robust Title Classifying Continuous Labels: A Simple Tweak to Make Regression Robust Author Bao, Ziyu (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor van Gemert, J.C. (mentor) Pintea, S. (mentor) Liem, C.C.S. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science Date 2022-07-04 Abstract Regression is difficult because of noise, imbalanced data sampling, missing data, etc. We propose a method by classifying the continuous regression labels to tackle regression robustness problems. We analyze if our method can help regression, given that the class information is already included in the regression labels. We start by extensively experimenting on 1D synthetic datasets and find out that classification can help regression when the data sampling is i balanced. This happens when the data are clean, noisy in inputs and noisy in outputs, but not when they are partially missing. We then validate our conclusion on the KITTI dataset by estimating 3D object orientation. We conclude that our method can help regression in real-world. Subject Robust RegressionComputer VisionLoss Functions To reference this document use: http://resolver.tudelft.nl/uuid:21a602e7-8a2e-403d-94bc-0202e4479b1d Part of collection Student theses Document type master thesis Rights © 2022 Ziyu Bao Files PDF Thesis_Report_ZBao.pdf 3.73 MB Close viewer /islandora/object/uuid%3A21a602e7-8a2e-403d-94bc-0202e4479b1d/datastream/OBJ/view