AI Paper Atlas

Research map / Detection and segmentation / CNN features

Boundary Flow: A Siamese Network That Predicts Boundary Motion Without Training on Motion

Peng Lei, Fuxin Li, Sinisa Todorovic

CVPR 2018 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 13 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
Use the Siamese FCSN for boundary detection instead of CEDNBoundary detection · VSB100ODS: 0.563 -> 0.597Improved
Use the Siamese FCSN for boundary detection instead of CEDNBoundary detection · VSB100AP: 0.547 -> 0.566Improved
Fine-tune on BSDS500 and VSB100 training setsFCSN · VSB100ODS: 0.597 -> 0.698Improved
Use edgelet-based matching instead of FLANNBoundary flow estimation · Sintel trainingEPE: $23.158$ -> $9.856$Improved
Use edgelet-based matching instead of RANSACBoundary flow estimation · Sintel trainingEPE: $20.874$ -> $9.856$Improved
Add boundary-flow matches to CPM-Flow inputCPM-Flow · Sintel final testEPE all: $5.960$ -> 5.645Improved
Add boundary-flow matches to CPM-Flow inputCPM-Flow · Sintel final testEPE unmatched: $30.177$ -> \textbf{29.362}Improved
Add boundary-flow matches to CPM-Flow inputCPM-Flow · Sintel final testEPE matched: $2.990$ -> $2.737$Hurt

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