AI Paper Atlas

Research map / Detection and segmentation / CNN features

Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding

Michael Maire, Takuya Narihira, Stella X. Yu

CVPR 2016 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 61 citations (OpenAlex)

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
Replace Maire's figure/ground method with Affinity CNNBSDS figure/ground predictions evaluated on ground-truth segmentation · BSDSR-ACC: 0.56 -> 0.62Improved
Replace Maire's figure/ground method with Affinity CNNBSDS figure/ground predictions evaluated on ground-truth segmentation · BSDSB-ACC: 0.58 -> 0.69Improved
Replace Maire's figure/ground method with Affinity CNNBSDS figure/ground predictions evaluated on ground-truth segmentation · BSDSB-ACC-50: 0.56 -> 0.72Improved
Replace Maire's figure/ground method with Affinity CNNBSDS figure/ground predictions evaluated on ground-truth segmentation · BSDSB-ACC-25: 0.56 -> 0.73Improved
Replace Maire's figure/ground method with Affinity CNNBSDS figure/ground predictions evaluated on Affinity CNN segmentation · BSDSR-ACC: 0.59 -> 0.66Improved
Replace Maire's figure/ground method with Affinity CNNBSDS figure/ground predictions evaluated on Affinity CNN segmentation · BSDSB-ACC: 0.62 -> 0.70Improved
Replace Maire's figure/ground method with Affinity CNNBSDS figure/ground predictions evaluated on Affinity CNN segmentation · BSDSB-ACC-50: 0.61 -> 0.69Improved
Replace Maire's figure/ground method with Affinity CNNBSDS figure/ground predictions evaluated on Affinity CNN segmentation · BSDSB-ACC-25: 0.58 -> 0.67Improved
Use Affinity CNN spectral boundaries instead of the gPb spectral componentBSDS boundary detection · BSDSF-measure: 0.68 -> 0.68No 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