AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Deep Dual Learning for Semantic Image Segmentation

Ping Luo, Guangrun Wang, Liang Lin, Xiaogang Wang

ICCV 2017 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 95 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 dual-learning inference refinement of labelmaps and tags during training (ttr=0 to ttr=5, tts=0) (ablation)DIS · VOC12 testmIoU: 80.0 -> 84.6Improved
increase training inference iterations from ttr=5 to ttr=30 with tts=0 (ablation)DIS · VOC12 testmIoU: 84.6 -> 86.3Improved
increase test inference iterations from tts=0 to tts=30 at ttr=5 (ablation)DIS · VOC12 testmIoU: 84.6 -> 86.2Improved
increase test inference iterations tts=0 to tts=30 at ttr=10 (ablation)DIS · VOC12 testmIoU: 85.5 -> 86.4Improved
increase test inference iterations tts=0 to tts=30 at ttr=30 (ablation)DIS · VOC12 testmIoU: 86.3 -> 86.8Improved
increase ttr from 5 to 30 at tts=10 (ablation)DIS · VOC12 testmIoU: 85.4 -> 86.5Improved
semi-supervised scheme without refinement (ttr=0) vs ResNet101 baseline (ablation)ResNet101 baseline · VOC12 testmIoU: outperforms the baseline by 5.8%Improved
replace WSSL+IDW with DIS using the same weak dataWSSL+IDW · VOC12 testmIoU: 81.9 -> 86.8Improved
add IDW weak tags to WSSLWSSL (semi) · VOC12 testmIoU: 69.0 -> 81.9Improved
increase training inference iterations from ttr=10 to ttr=30 at tts=0 (ablation)DIS · IDW testmIoU: 56.6 -> 57.5Improved
increase test iterations tts=0 to tts=30 at ttr=30 (ablation)DIS · IDW testmIoU: 57.5 -> 59.8Improved
DIS ttr=30, tts=30 vs WSSL+IDWWSSL+IDW · IDW testmIoU: 52.0 -> 59.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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