AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

XNet: Wavelet-Based Low and High Frequency Fusion Networks for Fully- and Semi-Supervised Semantic Segmentation of Biomedical Images

Yanfeng Zhou, Jiaxing Huang, Chenlong Wang, Le Song, Ge Yang

ICCV 2023 · Label-efficient and robust learning › Semi-supervised learning · approach: Semi-supervised medical segmentation · 155 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
feed wavelet LF and HF images through separate encoders with a fusion module (ablation)XNet · GlaS fully-supervisedJaccard index: 75.82 -> 84.77Improved
add LF/HF fusion module (semi-supervised) (ablation)XNet · GlaS semi-supervisedJaccard index: 66.78 -> 80.89Improved
use only HF images as input (ablation)XNet · GlaS fully-supervisedJaccard index: 82.03 -> 54.50Hurt
use LF and HF images as input without fusion (ablation)XNet · GlaS semi-supervisedJaccard index: 78.52 -> 66.78Hurt
use Db 2 wavelet basis instead of Dmey (ablation)XNet · GlaS semi-supervisedJaccard index: 73.95 -> 80.89Improved
use 2 LF and 2 HF fusion features rather than 3 and 3 (ablation)XNet · GlaS semi-supervisedJaccard index: 78.39 -> 80.89Improved
scale UNet up to XNet's parameter count (ablation)UNet · GlaS fully-supervisedJaccard index: 81.54 -> 82.73Improved
halve XNet channels (ablation)XNet · GlaS fully-supervisedJaccard index: 84.77 -> 83.49No clear effect
add unlabeled images to 20% labeled data (ablation)XNet · GlaSJaccard index: 69.84 -> 80.89Improved
apply XNet to images with little high-frequency information (ISIC-2017)XNet · ISIC-2017Jaccard index: 74.49 -> 73.94Hurt

Later papers that compared with this method

1 later accepted paper reports XNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy