AI Paper Atlas

Research map / Detection and segmentation / CNN features

Triply Supervised Decoder Networks for Joint Detection and Segmentation

Jiale Cao, Yanwei Pang, Xuelong Li

CVPR 2019 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 76 citations (OpenAlex)

Check 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
Jointly supervise detection and segmentation on each decoder layer (ablation)PairNet · VOC12-val-segmAP: 78.0 -> 78.9Improved
Jointly supervise detection and segmentation on each decoder layer (ablation)PairNet · VOC12-val-segmIoU: 72.9 -> 73.1Improved
Use segmentation supervision at all decoder layers instead of only the fine layer (ablation)PairNet · VOC12-val-segmIoU: 72.5 -> 72.9Improved
Add multiscale fused segmentation (ablation)PairNet · VOC12-val-segmAP: 78.9 -> 79.0Improved
Add multiscale fused segmentation (ablation)PairNet · VOC12-val-segmIoU: 73.1 -> 73.5Improved
Add the inner-connected module alongside MFS (ablation)PairNet · VOC12-val-segmAP: 79.0 -> 79.5Improved
Add the inner-connected module alongside MFS (ablation)PairNet · VOC12-val-segmIoU: 73.5 -> 73.6Improved
Add class-agnostic segmentation supervision to the MFS-and-IC variant (ablation)PairNet · VOC12-val-segmAP: 79.5 -> 79.7Improved
Add class-agnostic segmentation supervision to the MFS-and-IC variant (ablation)PairNet · VOC12-val-segmIoU: 73.6 -> 74.4Improved
Add attention skip-layer fusion to the preceding variant (ablation)PairNet · VOC12-val-segmAP: 79.7 -> 80.0Improved
Add attention skip-layer fusion to the preceding variant (ablation)PairNet · VOC12-val-segmIoU: 74.4 -> 74.8Improved
Use TripleNet instead of BlitzNetJoint detection and segmentation · VOC12-testmAP: 79.0 -> 81.0Improved

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