Research map / Detection and segmentation / CNN features
Triply Supervised Decoder Networks for Joint Detection and Segmentation
Jiale Cao, Yanwei Pang, Xuelong Li
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Jointly supervise detection and segmentation on each decoder layer (ablation) | PairNet · VOC12-val-seg | mAP: 78.0 -> 78.9 | Improved |
| Jointly supervise detection and segmentation on each decoder layer (ablation) | PairNet · VOC12-val-seg | mIoU: 72.9 -> 73.1 | Improved |
| Use segmentation supervision at all decoder layers instead of only the fine layer (ablation) | PairNet · VOC12-val-seg | mIoU: 72.5 -> 72.9 | Improved |
| Add multiscale fused segmentation (ablation) | PairNet · VOC12-val-seg | mAP: 78.9 -> 79.0 | Improved |
| Add multiscale fused segmentation (ablation) | PairNet · VOC12-val-seg | mIoU: 73.1 -> 73.5 | Improved |
| Add the inner-connected module alongside MFS (ablation) | PairNet · VOC12-val-seg | mAP: 79.0 -> 79.5 | Improved |
| Add the inner-connected module alongside MFS (ablation) | PairNet · VOC12-val-seg | mIoU: 73.5 -> 73.6 | Improved |
| Add class-agnostic segmentation supervision to the MFS-and-IC variant (ablation) | PairNet · VOC12-val-seg | mAP: 79.5 -> 79.7 | Improved |
| Add class-agnostic segmentation supervision to the MFS-and-IC variant (ablation) | PairNet · VOC12-val-seg | mIoU: 73.6 -> 74.4 | Improved |
| Add attention skip-layer fusion to the preceding variant (ablation) | PairNet · VOC12-val-seg | mAP: 79.7 -> 80.0 | Improved |
| Add attention skip-layer fusion to the preceding variant (ablation) | PairNet · VOC12-val-seg | mIoU: 74.4 -> 74.8 | Improved |
| Use TripleNet instead of BlitzNet | Joint detection and segmentation · VOC12-test | mAP: 79.0 -> 81.0 | Improved |
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.
- BlitzNet300 — BlitzNet: A Real-Time Deep Network for Scene Understanding (ICCV 2017) · better on 4 of 4 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
- BlitzNet: A Real-Time Deep Network for Scene Understanding (ICCV 2017 · similarity 0.87)
- Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving (AAAI 2022 · similarity 0.87)
- A Holistically-Guided Decoder for Deep Representation Learning With Applications to Semantic Segmentation and Object Detection (TPAMI 2021 · similarity 0.87)
- Instance-Aware Semantic Segmentation via Multi-Task Network Cascades (CVPR 2016 · similarity 0.87)
- Mr. DETR++: Instructive Multi-Route Training for Detection Transformers with Mixture-of-Experts (TPAMI 2026 · similarity 0.86)
- DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation (ICLR 2025 · similarity 0.85)
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.
