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

Recent advances in denoising diffusion probabilistic models have shown greatsuccess in image synthesis tasks. While there are already works exploring thepotential of this powerful tool in image semantic segmentation, its applicationin weakly supervised semantic segmentation (WSSS) remains relativelyunder-explored. Observing that conditional diffusion models (CDM) is capable ofgenerating images subject to specific distributions, in this work, we utilizecategory-aware semantic information underlied in CDM to get the prediction maskof the target object with only image-level annotations. More specifically, welocate the desired class by approximating the derivative of the output of CDMw.r.t the input condition. Our method is different from previous diffusionmodel methods with guidance from an external classifier, which accumulatesnoises in the background during the reconstruction process. Our methodoutperforms state-of-the-art CAM and diffusion model methods on two publicmedical image segmentation datasets, which demonstrates that CDM is a promisingtool in WSSS. Also, experiment shows our method is more time-efficient thanexisting diffusion model methods, making it practical for wider applications.

Conditional Diffusion Models for Weakly Supervised Medical Image Segmentation