AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Convolutional Oriented Boundaries

Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Pablo Arbeláez, Luc Van Gool

ECCV 2016 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 140 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
add trained orientations and drop globalization (final COB system) (ablation)COB (ResNet50) · PASCAL Context VOC valboundary and region F-measureImproved
add globalization on top of trained orientations (ablation)COB · PASCAL Context VOC valboundary and region qualityHurt
replace VGGNet base with ResNet50 (ablation)COB · PASCAL Context VOC valboundary and region qualityImproved
use trained orientations instead of local gradient orientation estimationCOB · Contour orientation (8 bins)area under accuracy curve (%): 41.2 -> 58.6Improved
use sparse boundaries representation for OWT and UCMMCG-HED · PASCAL Context timingOWT and UCM time (s): 11.58 -> 1.63Improved
remove globalization, compute three scales in one pass, add orientationsFast UCMs · PASCAL Context timingtotal time (s): 24.37 -> 0.79Improved

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