Weakly Supervised YOLO Network for Surgical Instrument Localization in Endoscopic Videos
This addresses the problem of tedious annotation for surgical instrument localization in minimally invasive surgery, offering an incremental improvement by leveraging easier-to-obtain category data.
The paper tackles surgical instrument localization in endoscopic videos by proposing WS-YOLO, a weakly supervised framework that uses category information as weak supervision, achieving remarkable performance on the Endoscopic Vision Challenge 2023 dataset.
In minimally invasive surgery, surgical instrument localization is a crucial task for endoscopic videos, which enables various applications for improving surgical outcomes. However, annotating the instrument localization in endoscopic videos is tedious and labor-intensive. In contrast, obtaining the category information is easy and efficient in real-world applications. To fully utilize the category information and address the localization problem, we propose a weakly supervised localization framework named WS-YOLO for surgical instruments. By leveraging the instrument category information as the weak supervision, our WS-YOLO framework adopts an unsupervised multi-round training strategy for the localization capability training. We validate our WS-YOLO framework on the Endoscopic Vision Challenge 2023 dataset, which achieves remarkable performance in the weakly supervised surgical instrument localization. The source code is available at https://github.com/Breezewrf/WS-YOLO.