AI Paper Atlas

Research map / Detection and segmentation / CNN features

Non-Local U-Nets for Biomedical Image Segmentation

Zhengyang Wang, Na Zou, Dinggang Shen, Shuiwang Ji

AAAI 2020 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 196 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
Replace local-only CC-3D-FCN with non-local U-Net global aggregation blocksCC-3D-FCN · iSeg infant brain MR, leave-one-subject-outAverage Dice ratio: 0.9087$\pm$0.0066 -> 0.9292$\pm$0.0050Improved
Replace local-only CC-3D-FCN with non-local U-Net global aggregation blocksCC-3D-FCN · iSeg infant brain MR, leave-one-subject-outAverage 3D-MHD: 0.4924$\pm$0.0345 -> 0.4319$\pm$0.0313Improved
Replace CC-3D-FCN with non-local U-NetCC-3D-FCN · iSeg infant brain MRNumber of parameters: 2,534,276 -> 1,821,124Improved
Replace CC-3D-FCN with non-local U-NetCC-3D-FCN · iSeg infant brain MR, patch size $32^3$, overlap step 8Inference time (min): 3.85$\pm$0.15 -> 3.06$\pm$0.12Improved
Add short-range residual connections (ablation)Model1 · 10th subject, ablationAverage Dice ratio: 0.9103 -> 0.9156Improved
Add short-range residual connections (ablation)Model1 · 10th subject, ablationAverage 3D-MHD: 0.4448 -> 0.4312Improved
Replace the first up-sampling block with an up-sampling global aggregation block (ablation)Model2 · 10th subject, ablationAverage Dice ratio: 0.9156 -> 0.9174Improved
Replace the first up-sampling block with an up-sampling global aggregation block (ablation)Model2 · 10th subject, ablationAverage 3D-MHD: 0.4312 -> 0.4271Improved
Replace both up-sampling blocks with up-sampling global aggregation blocks (ablation)Model2 · 10th subject, ablationAverage Dice ratio: 0.9156 -> 0.9186Improved
Replace both up-sampling blocks with up-sampling global aggregation blocks (ablation)Model2 · 10th subject, ablationAverage 3D-MHD: 0.4312 -> 0.4220Improved
Replace the bottom block with a global aggregation block (ablation)Model2 · 10th subject, ablationAverage Dice ratio: 0.9156 -> 0.9194Improved
Replace the bottom block with a global aggregation block (ablation)Model2 · 10th subject, ablationAverage 3D-MHD: 0.4312 -> 0.4211Improved

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