AI Paper Atlas

Research map / Detection and segmentation / CNN features

Occlusion Boundary Detection via Deep Exploration of Context

Huan Fu, Chaohui Wang, Dacheng Tao, Michael J. Black

CVPR 2016 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 28 citations (OpenAlex)

Check 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 proposed CNN-CRF detector with probabilistic outputOcclusion boundary detection · CMU benchmarkF-measure: 0.62 -> 0.71Improved
Add both motion features OMF1 and OMF2 to image cues (ablation)Occlusion boundary detector · CMU benchmarkF-measure: 0.60 -> 0.71Improved
Add OMF2 while retaining OMF1 (ablation)Occlusion boundary detector · CMU benchmarkF-measure: 0.65 -> 0.71Improved
Add OMF1 while retaining OMF2 (ablation)Occlusion boundary detector · CMU benchmarkF-measure: 0.64 -> 0.71Improved
Replace Classic-NL with LDOF optical flow (ablation)Occlusion boundary detector · CMU benchmarkF-measure: 0.71 -> 0.68Hurt
Replace Classic-NL with Deepflow optical flow (ablation)Occlusion boundary detector · CMU benchmarkF-measure: 0.71 -> 0.69Hurt
Replace Classic-NL with Sun et al. optical flow (ablation)Occlusion boundary detector · CMU benchmarkF-measure: 0.71No clear effect
Map a large patch to its center pixel instead of a small structured patch (ablation)CNN context model · CMU benchmarkF-measure: 0.71 -> 0.66Hurt
Predict each pixel in the small output patch independently (ablation)CNN context model · CMU benchmarkF-measure: 0.71 -> 0.65Hurt
Predict an output patch the same size as the input patch (ablation)CNN context model · CMU benchmarkF-measure: 0.71 -> 0.66Hurt
Use a small patch as both the CNN input and output (ablation)CNN context model · CMU benchmarkF-measure: 0.71 -> 0.63Hurt

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