AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Neural Diffusion Distance for Image Segmentation

Jian Sun, Zongben Xu

NeurIPS 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 7 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
share classifier between classification and segmentation (ablation)weakly supervised segmentation network · PASCAL VOC 2012 valmIoU: 64.7 -> 65.8Improved
use diffusion distance instead of embedding similarity (ablation)weakly supervised segmentation network · PASCAL VOC 2012 valmIoU: 54.7 -> 65.8Improved
replace global average pooling with PC-WAP and RFPweakly supervised segmentation network · PASCAL VOC 2012 valmIoU: 45.2 -> 65.8Improved
add feature-attentional interpolation of segmentation masks (HR) (ablation)hierarchical segmentation · BSD500 testcovering MAX: 0.78 -> 0.80Improved
add feature-attentional interpolation of segmentation masks (HR) (ablation)hierarchical segmentation · BSD500 testcovering AVR: 0.68 -> 0.69Improved
replace DeepNCut with neural diffusion distance (HR)hierarchical segmentation · BSD500 testcovering MAX: 0.70 -> 0.80Improved
replace NCut-DF with neural diffusion distance (HR)hierarchical segmentation · BSD500 testcovering AVR: 0.48 -> 0.69Improved
increase iterations T from 1 to 2 at t=10 (ablation)spec-diff-net · BSD500 testcosine similarity: 0.709 -> 0.741Improved
increase initial t from 5 to 10 at T=2 (ablation)spec-diff-net · BSD500 testcosine similarity: 0.738 -> 0.741Improved
increase initial t from 5 to 10 at T=1 (ablation)spec-diff-net · BSD500 train+valcosine similarity: 0.778 -> 0.785Improved
increase iterations T from 2 to 3 at t=5 (ablation)spec-diff-net · BSD500 train+valcosine similarity: 0.785 -> 0.777No clear effect
increase iterations T from 2 to 3 at t=10 (ablation)spec-diff-net · BSD500 train+valcosine similarity: 0.794 -> 0.785Hurt

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