This is the latest version of this eprint.
Pan, Z, Jiang, P, Wang, Y et al. (2 more authors) (2022) Scribble-Supervised Semantic Segmentation by Uncertainty Reduction on Neural Representation and Self-Supervision on Neural Eigenspace. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV). 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 10-17 Oct 2021, Montreal, QC, Canada. IEEE , pp. 7396-7405. ISBN 978-1-6654-2813-2
Abstract
Scribble-supervised semantic segmentation has gained much attention recently for its promising performance without high-quality annotations. Due to the lack of supervision, confident and consistent predictions are usually hard to obtain. Typically, people handle these problems by either adopting an auxiliary task with the well-labeled dataset or incorporating a graphical model with additional requirements on scribble annotations. Instead, this work aims to achieve semantic segmentation by scribble annotations directly without extra information and other limitations. Specifically, we propose holistic operations, including minimizing entropy and a network embedded random walk on the neural representation to reduce uncertainty. Given the probabilistic transition matrix of a random walk, we further train the network with self-supervision on its neural eigenspace to impose consistency on predictions between related images. Comprehensive experiments and ablation studies verify the proposed approach, which demonstrates superiority over others; it is even comparable to some full-label supervised ones and works well when scribbles are randomly shrunk or dropped.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
Keywords: | Visualization, Image segmentation, Computer vision, Uncertainty, Graphical models, Annotations, Semantics |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Funding Information: | Funder Grant number EU - European Union 825619 |
Depositing User: | Symplectic Publications |
Date Deposited: | 14 Oct 2021 12:05 |
Last Modified: | 21 Nov 2024 15:48 |
Status: | Published |
Publisher: | IEEE |
Identification Number: | 10.1109/ICCV48922.2021.00732 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:179224 |
Available Versions of this Item
-
Scribble-Supervised Semantic Segmentation by Uncertainty Reduction on Neural Representation and Self-Supervision on Neural Eigenspace. (deposited 01 Oct 2024 13:56)
- Scribble-Supervised Semantic Segmentation by Uncertainty Reduction on Neural Representation and Self-Supervision on Neural Eigenspace. (deposited 14 Oct 2021 12:05) [Currently Displayed]