English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Surgical instrument segmentation in robot-assisted surgery (RAS) - especiallythat using learning-based models - relies on the assumption that training andtesting videos are sampled from the same domain. However, it is impractical andexpensive to collect and annotate sufficient data from every new domain. Togreatly increase the label efficiency, we explore a new problem, i.e., adaptiveinstrument segmentation, which is to effectively adapt one source model to newrobotic surgical videos from multiple target domains, only given the annotatedinstruments in the first frame. We propose MDAL, a meta-learning based dynamiconline adaptive learning scheme with a two-stage framework to fast adapt themodel parameters on the first frame and partial subsequent frames whilepredicting the results. MDAL learns the general knowledge of instruments andthe fast adaptation ability through the video-specific meta-learning paradigm.The added gradient gate excludes the noisy supervision from pseudo masks fordynamic online adaptation on target videos. We demonstrate empirically thatMDAL outperforms other state-of-the-art methods on two datasets (including areal-world RAS dataset). The promising performance on ex-vivo scenes alsobenefits the downstream tasks such as robot-assisted suturing and cameracontrol.

One to Many: Adaptive Instrument Segmentation via Meta Learning and Dynamic Online Adaptation in Robotic Surgical Video