AI Paper Atlas

Research map / Detection and segmentation / CNN features

Deep Learning Markov Random Field for Semantic Segmentation

Ziwei Liu, Xiaoxiao Li, Ping Luo, Chen Change Loy, Xiaoou Tang

TPAMI 2017 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 186 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 triple penalty (b12) to unary term (ablation)DPN · VOC12 valmIoU: 62.4 -> 64.7Improved
add mixture of label contexts (b13) (ablation)DPN · VOC12 valmIoU: 64.7 -> 66.5Improved
add joint fine-tuning of all components (ablation)DPN · VOC12 valmIoU: 66.5 -> 67.8Improved
enlarge b12 receptive field from 10x10 to 50x50 (ablation)DPN · VOC12 valmIoU: 63.8 -> 64.7Improved
enlarge b12 receptive field from 50x50 to 100x100 (ablation)DPN · VOC12 valmIoU: 64.7 -> 64.3No clear effect
enlarge b13 receptive field from 1x1 to 5x5 (ablation)DPN · VOC12 valmIoU: 64.8 -> 66.0Improved
use 9x9 mixtures instead of single 9x9 filter in b13 (ablation)DPN · VOC12 valmIoU: 66.3 -> 66.5Improved
use DPN pairwise terms instead of DSN or DeepLab pairwise terms (ablation)DPN · VOC12 valimprovement over unary (%): 2.6 -> 5.4Improved
use 3D spatial-temporal pairwise term instead of 2DDPN · CamVid testmIoU: 60.06 -> 60.25Improved
incremental learning instead of joint learning from the start (ablation)DPN · VOC12 valtraining accuracy curveImproved
use one MF iteration instead of 5 or more (ablation)DPN · VOC12 valaccuracyNo clear effect
add COCO pre-trainingDPN · VOC12 testmIoU: 74.1 -> 77.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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