Print Email Facebook Twitter Feasibility study of "Invariant Information Clustering for Unsupervised Image Segmentation" Title Feasibility study of "Invariant Information Clustering for Unsupervised Image Segmentation" Author Dimitrov, Yordan (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Lengyel, A. (mentor) Pintea, S. (mentor) Tömen, N. (mentor) van Gemert, J.C. (mentor) Degree granting institution Delft University of Technology Date 2021-10-22 Abstract In this paper we analyze the performance of a novel clustering objective that optimizes a neural network to predict segmentation. We challenge the reported results by replicating the original experiments and conducting additional tests to gain an insight into the algorithm. We analyzed the efficiency of the clustering objective on a different architecture, dataset and hyper-parameters. To our surprise the algorithm demonstrated considerably lower results when running on the new setup. Further, in our work we detail the reasons behind the discrepancy and provide configurations under which the method performs best. We show that the objective is highly sensitive to the type of images it is predicting and the complexity of the architecture that is being used with. Subject SegmentationUnsupervised learningMutual InformationFeasebility studyExperiment setupBoundary effectsAugmentation To reference this document use: http://resolver.tudelft.nl/uuid:21248d5f-bfde-4805-811f-e0db76289d67 Part of collection Student theses Document type master thesis Rights © 2021 Yordan Dimitrov Files PDF Feasibility_study_of_Inva ... tation.pdf 9.79 MB Close viewer /islandora/object/uuid:21248d5f-bfde-4805-811f-e0db76289d67/datastream/OBJ/view