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/

Zendy Plus

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

Zendy Tools

Zendy Open

The "pre-training then fine-tuning (FT)" paradigm is widely adopted to boostthe model performance of deep learning-based methods for medical volumetricsegmentation. However, conventional full FT incurs high computational andmemory costs. Thus, it is of increasing importance to fine-tune pre-trainedmodels for medical volumetric segmentation tasks in a both effective andparameter-efficient manner. In this paper, we introduce a new framework namedMed-Tuning to realize parameter-efficient tuning (PET) for medical volumetricsegmentation task and an efficient plug-and-play module named Med-Adapter fortask-specific feature extraction. With a small number of tuned parameters, ourframework enhances the 2D baselines's precision on segmentation tasks, whichare pre-trained on natural images. Extensive experiments on three benchmarkdatasets (CT and MRI modalities) show that our method achieves better resultsthan previous PET methods on volumetric segmentation tasks. Compared to fullFT, Med-Tuning reduces the fine-tuned model parameters by up to 4x, with evenbetter segmentation performance. Our project webpage is at\url{https://rubics-xuan.github.io/Med-Tuning/}.

Med-Tuning: A New Parameter-Efficient Tuning Framework for Medical Volumetric Segmentation