AI Paper Atlas

Research map / Detection and segmentation / CNN features

Graph-without-cut: An Ideal Graph Learning for Image Segmentation

Lianli Gao, Jingkuan Song, Feiping Nie, Fuhao Zou, Nicu Sebe, Heng Tao Shen

AAAI 2016 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 38 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
learn similarity graph with rank-constrained Laplacian (GWC) instead of separate graph + cut (gPb)graph-based segmentation · BSDS500Covering ODS: 0.59 -> 0.61Improved
GWC instead of ISCRAimage segmentation · MSRCVI ODS: 1.18 -> 1.24Hurt
GWC instead of MCGimage segmentation · BSDS500VI ODS: 1.55 -> 1.62Hurt
GWC instead of DCimage segmentation · BSDS500all metrics: 0.59 -> 0.61 Covering ODSImproved
increase visual feature weight mu from below 10^2 (ablation)GWC · BSDS500Covering/PRI ODSImproved
vary gamma (feature weight regularization) (ablation)GWC · BSDS500Covering/PRI ODSNo clear effect

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