DaWeaklyMHPSemSeg

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

Master's thesis

Supervision by: Iro Laina, Christian Rupprecht, Federico Tombari
Thesis by: Marat Seroglazov

Abstract

During the past few years, remarkable progress has been made in the field of semantic image segmentation, thanks to deep learning and CNN advances. However, it remains challenging to reach a high accuracy using training data with image-level annotations only, i.e. in a weakly supervised fashion. In this project, we address the problem of semantic segmentation from image-level labels together with a small percentage of pixel-wise labeled images. Our approach will begin from recent work in estimating class-specific saliency maps [1]. Our goal is to further enhance its training pipeline, introduce a multiple hypothesis prediction approach [2] for improving the quality of the semantic outputs and additionally explore its usability for instance segmentation.

Resources

[1] Shimoda, Wataru, and Keiji Yanai. "Distinct class-specific saliency maps for weakly supervised semantic segmentation." In European Conference on Computer Vision, pp. 218-234. Springer, Cham, 2016.
[2] Rupprecht, Christian, Iro Laina, Robert DiPietro?, Maximilian Baust, Federico Tombari, Nassir Navab, and Gregory D. Hager. "Learning in an uncertain world: Representing ambiguity through multiple hypotheses." In International Conference on Computer Vision (ICCV). 2017.

Students.ProjectForm
Title: Weakly supervised semantic segmentation via multiple hypothesis prediction
Abstract: During the past few years, remarkable progress has been made in the field of semantic image segmentation, thanks to deep learning and CNN advances. However, it remains challenging to reach a high accuracy using training data with image-level annotations only, i.e. in a weakly supervised fashion. In this project, we address the problem of semantic segmentation from image-level labels together with a small percentage of pixel-wise labeled images. Our approach will begin from recent work in estimating class-specific saliency maps [1]. Our goal is to further enhance its training pipeline, introduce a multiple hypothesis prediction approach [2] for improving the quality of the semantic outputs and additionally explore its usability for instance segmentation. [1] Shimoda, Wataru, and Keiji Yanai. "Distinct class-specific saliency maps for weakly supervised semantic segmentation." In European Conference on Computer Vision, pp. 218-234. Springer, Cham, 2016. [2] Rupprecht, Christian, Iro Laina, Robert DiPietro?, Maximilian Baust, Federico Tombari, Nassir Navab, and Gregory D. Hager. "Learning in an uncertain world: Representing ambiguity through multiple hypotheses." In International Conference on Computer Vision (ICCV). 2017.
Student: Marat Seroglazov
Director: Nassir Navab
Supervisor: Iro Laina, Christian Rupprecht, Federico Tombari
Type: DA/MA/BA
Area:  
Status: running
Start: 15.01.2017
Finish: 15.09.2018
Thesis (optional):  
Picture:  


Edit | Attach | Refresh | Diffs | More | Revision r1.2 - 13 Feb 2018 - 13:31 - IroLaina