Balancing Bounding Box and Mask Annotations for Semi-Supervised Instance Segmentation
| dc.contributor.author | Tolstykh, Daniil | |
| dc.contributor.author | Slutskiy, Dmitriy | |
| dc.contributor.editor | Skala, Václav | |
| dc.date.accessioned | 2025-07-30T09:18:15Z | |
| dc.date.available | 2025-07-30T09:18:15Z | |
| dc.date.issued | 2025 | |
| dc.description.abstract-translated | Instance segmentation models are crucial for precise object detection but often require expensive pixel-wise mask annotations. This paper studies the impact of combining bounding box and mask annotations in semi-supervised segmentation. We propose a method that leverages from both types of labeled data within a unified training framework. Through experiments on YOLO (convolution-based) and DETR (transformer-based) architectures, we demonstrate that balancing these annotation types significantly enhances performance while reducing labeling costs, particularly in terms of manual annotation time. Additionally, we evaluate few-shot and zero-shot scenarios, further highlighting the flexibility and efficiency of our method for budget-constrained segmentation tasks. | en |
| dc.description.sponsorship | The authors express their gratitude to Irene De Teresa Trueba and the anonymous referees for their valuable comments, which significantly enhanced the readability of this text. Additionally, the authors extend their thanks to Fabrice Boudaud and the CSAI Lab of ENGIE CRIGEN for their support in this work. | |
| dc.format | 12 s. | cs |
| dc.format.mimetype | application/pdf | |
| dc.identifier.doi | http://www.doi.org/10.24132/CSRN.2025-9 | |
| dc.identifier.issn | 2464-4617 (Print) | |
| dc.identifier.issn | 2464-4625 (online) | |
| dc.identifier.uri | http://hdl.handle.net/11025/62215 | |
| dc.language.iso | en | en |
| dc.publisher | Vaclav Skala - UNION Agency | en |
| dc.rights | © Vaclav Skala - UNION Agency | en |
| dc.rights.access | openAccess | en |
| dc.subject | segmentace instancí | cs |
| dc.subject | polo-supervizované učení | cs |
| dc.subject | optimalizace nákladů na označování | cs |
| dc.subject | YOLOv5 | cs |
| dc.subject | DETR | cs |
| dc.subject.translated | instance segmentation | en |
| dc.subject.translated | semi-supervised learning | en |
| dc.subject.translated | labeling cost optimization | en |
| dc.subject.translated | YOLOv5 | en |
| dc.subject.translated | DETR | en |
| dc.title | Balancing Bounding Box and Mask Annotations for Semi-Supervised Instance Segmentation | en |
| dc.type | konferenční příspěvek | cs |
| dc.type | conferenceObject | en |
| dc.type.status | Peer reviewed | en |
| dc.type.version | publishedVersion | en |
| local.files.count | 1 | * |
| local.files.size | 8313401 | * |
| local.has.files | yes | * |