AI Paper Atlas

Research map / Detection and segmentation / CNN features

Segmentation from Natural Language Expressions

Ronghang Hu, Marcus Rohrbach, Trevor Darrell

ECCV 2016 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 483 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 deconvolution upsampling and fine-tune a high resolution model over the low resolution model (ablation)Ours · ReferIt testprecision@0.5: 29.54% -> 34.02%Improved
add deconvolution upsampling and fine-tune a high resolution model over the low resolution model (ablation)Ours · ReferIt testprecision@0.7: 13.69% -> 19.32%Improved
add deconvolution upsampling and fine-tune a high resolution model over the low resolution model (ablation)Ours · ReferIt testprecision@0.9: 0.75% -> 3.92%Improved
add deconvolution upsampling and fine-tune a high resolution model over the low resolution model (ablation)Ours · ReferIt testoverall IoU: 45.57% -> 48.03%Improved
average per-word scores rather than intersect or union them (ablation)per-word segmentation baseline · ReferIt testoverall IoU: 26.69% -> 27.23%Improved
average per-word scores rather than take their union (ablation)per-word segmentation baseline · ReferIt testoverall IoU: 19.37% -> 27.23%Improved
apply GrabCut to the box instead of using the whole bounding box (ablation)SCRC · ReferIt testprecision@0.5: 9.73% -> 11.91%Improved
apply GrabCut to the box instead of using the whole bounding box (ablation)GroundeR · ReferIt testprecision@0.5: 11.08% -> 14.09%Improved
apply GrabCut to the box instead of using the whole bounding box (ablation)SCRC · ReferIt testoverall IoU: 21.72% -> 17.84%Hurt
apply GrabCut to the box instead of using the whole bounding box (ablation)GroundeR · ReferIt testoverall IoU: 20.50% -> 20.09%Hurt
use the end-to-end recurrent convolutional model instead of proposal-based GrabCut/MCG pipelinessegmentation from expressions · ReferIt testaverage time per input (sec): 9.375 -> 0.325Improved
use the full model instead of the per-word segmentation baselinesegmentation from expressions · ReferIt testaverage time per input (sec): 0.169 -> 0.325Hurt

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