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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep learning-based medical volumetric segmentation methods either train themodel from scratch or follow the standard ``pre-training then fine-tuning"paradigm. Although fine-tuning a pre-trained model on downstream tasks canharness its representation power, the standard full fine-tuning is costly interms of computation and memory footprint. In this paper, we present the studyon parameter-efficient transfer learning for medical volumetric segmentationand propose a new framework named Med-Tuning based on intra-stage featureenhancement and inter-stage feature interaction. Additionally, aiming atexploiting the intrinsic global properties of Fourier Transform forparameter-efficient transfer learning, a new adapter block namely Med-Adapterwith a well-designed Fourier Transform branch is proposed for effectively andefficiently modeling the crucial global context for medical volumetricsegmentation. Given a large-scale pre-trained model on 2D natural images, ourmethod can exploit both the crucial spatial multi-scale feature and volumetriccorrelations along slices for accurate segmentation. Extensive experiments onthree benchmark datasets (including CT and MRI) show that our method canachieve better results than previous parameter-efficient transfer learningmethods on segmentation tasks, with much less tuned parameter costs. Comparedto full fine-tuning, our method reduces the fine-tuned model parameters by upto 4x, with even better segmentation performance. The code will be madepublicly available at https://github.com/jessie-chen99/Med-Tuning.

Med-Tuning: Parameter-Efficient Transfer Learning with Fine-Grained Feature Enhancement for Medical Volumetric Segmentation