AI Paper Atlas

Research map / Detection and segmentation / CNN features

Exploring Context with Deep Structured Models for Semantic Segmentation

Guosheng Lin, Chunhua Shen, Anton van den Hengel, Ian D. Reid

TPAMI 2017 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 134 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 sliding pyramid pooling (ablation)FullyConvNet baseline · NYUDv2 (40 classes)IoU: 30.5 -> 32.4Improved
add multi-scale inputs (ablation)FullyConvNet + pyramid pooling · NYUDv2 (40 classes)IoU: 32.4 -> 37.0Improved
add boundary refinement (ablation)FullyConvNet + multi-scales · NYUDv2 (40 classes)IoU: 37.0 -> 38.3Improved
add CNN contextual pairwise potentials (ablation)FCN with refinement · NYUDv2 (40 classes)IoU: 38.3 -> 40.6Improved
use 1 pairwise + 1 unary CRF instead of 4-unary ensemble (ablation)unary-only ensemble · NYUDv2 (40 classes)IoU: 38.7 -> 38.9Improved
add a second unary to the contextual CRF (ablation)1 pairwise + 1 unary · NYUDv2 (40 classes)IoU: 38.9 -> 39.2Improved
ensemble more unary-only networks (1 to 4) (ablation)unary network · NYUDv2 (40 classes)IoU: 37.0 -> 38.7Improved
add COCO pretraining/training dataours · PASCAL VOC 2012 testmean IoU: 75.3 -> 77.8Improved
use contextual CRF model instead of FullyConvNet + refineFullyConvNet + refine · COCO (80 classes)IoU: 41.3 -> 46.8Improved
use RGB-only contextual CRF instead of FCN-HHA using RGB-DFCN-HHA · NYUDv2 (40 classes)IoU: 34.0 -> 40.6Improved
add COCO pretrainingours · KITTIIoU: 68.5 -> 70.3Improved
add refinement to fully convolutional networkFullyConvNet · COCO (80 classes)mean accuracy: 56.9 -> 55.0Hurt

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