Details
| Original language | English |
|---|---|
| Title of host publication | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops |
| Subtitle of host publication | CVPRW 2023 |
| Publisher | IEEE Computer Society |
| Pages | 3267-3278 |
| Number of pages | 12 |
| ISBN (electronic) | 9798350302493 |
| ISBN (print) | 979-8-3503-0250-9 |
| Publication status | Published - 2023 |
| Event | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023 - Vancouver, Canada Duration: 17 Jun 2023 → 24 Jun 2023 |
Publication series
| Name | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops |
|---|---|
| Volume | 2023-June |
| ISSN (Print) | 2160-7508 |
| ISSN (electronic) | 2160-7516 |
Abstract
Label noise and ambiguities between similar classes are challenging problems in developing new models and annotating new data for semantic segmentation. In this paper, we propose Compensation Learning in Semantic Segmentation, a framework to identify and compensate ambiguities as well as label noise. More specifically, we add a ground truth depending and globally learned bias to the classification logits and introduce a novel uncertainty branch for neural networks to induce the compensation bias only to relevant regions. Our method is employed into state-of-the-art segmentation frameworks and several experiments demonstrate that our proposed compensation learns inter-class relations that allow global identification of challenging ambiguities as well as the exact localization of subsequent label noise. Additionally, it enlarges robustness against label noise during training and allows target-oriented manipulation during inference. We evaluate the proposed method on Cityscapes, KITTI-STEP, ADE20k, and COCO-stuff10k.
ASJC Scopus subject areas
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Engineering(all)
- Electrical and Electronic Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops: CVPRW 2023. IEEE Computer Society, 2023. p. 3267-3278 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2023-June).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Compensation Learning in Semantic Segmentation
AU - Kaiser, Timo
AU - Reinders, Christoph
AU - Rosenhahn, Bodo
N1 - Funding Information: This work was supported by the Federal Ministry of Education and Research (BMBF), Germany under the project LeibnizKILabor (grant no. 01DD20003) and the AI service center KISSKI (grant no. 01IS22093C), the Center for Digital Innovations (ZDIN) and the Deutsche Forschungs-gemeinschaft (DFG) under Germany’s Excellence Strategy within the Cluster of Excellence PhoenixD (EXC 2122).
PY - 2023
Y1 - 2023
N2 - Label noise and ambiguities between similar classes are challenging problems in developing new models and annotating new data for semantic segmentation. In this paper, we propose Compensation Learning in Semantic Segmentation, a framework to identify and compensate ambiguities as well as label noise. More specifically, we add a ground truth depending and globally learned bias to the classification logits and introduce a novel uncertainty branch for neural networks to induce the compensation bias only to relevant regions. Our method is employed into state-of-the-art segmentation frameworks and several experiments demonstrate that our proposed compensation learns inter-class relations that allow global identification of challenging ambiguities as well as the exact localization of subsequent label noise. Additionally, it enlarges robustness against label noise during training and allows target-oriented manipulation during inference. We evaluate the proposed method on Cityscapes, KITTI-STEP, ADE20k, and COCO-stuff10k.
AB - Label noise and ambiguities between similar classes are challenging problems in developing new models and annotating new data for semantic segmentation. In this paper, we propose Compensation Learning in Semantic Segmentation, a framework to identify and compensate ambiguities as well as label noise. More specifically, we add a ground truth depending and globally learned bias to the classification logits and introduce a novel uncertainty branch for neural networks to induce the compensation bias only to relevant regions. Our method is employed into state-of-the-art segmentation frameworks and several experiments demonstrate that our proposed compensation learns inter-class relations that allow global identification of challenging ambiguities as well as the exact localization of subsequent label noise. Additionally, it enlarges robustness against label noise during training and allows target-oriented manipulation during inference. We evaluate the proposed method on Cityscapes, KITTI-STEP, ADE20k, and COCO-stuff10k.
UR - http://www.scopus.com/inward/record.url?scp=85166780399&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2304.13428
DO - 10.48550/arXiv.2304.13428
M3 - Conference contribution
AN - SCOPUS:85166780399
SN - 979-8-3503-0250-9
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 3267
EP - 3278
BT - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
PB - IEEE Computer Society
T2 - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
Y2 - 17 June 2023 through 24 June 2023
ER -