Research map / Detection and segmentation / CNN features
Boundary-Aware Feature Propagation for Scene Segmentation
Henghui Ding, Xudong Jiang, Ai Qun Liu, Nadia Magnenat Thalmann, Gang Wang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add unidirectional acyclic graph (UAG) propagation to dilated FCN (ResNet-50) (ablation) | FCN · PASCAL-Context (59 classes) | mIoU (%): 41.2 -> 49.8 | Improved |
| switch backbone from ResNet-50 to ResNet-101 (ablation) | BFP with UAGs · PASCAL-Context (59 classes) | mIoU (%): 49.8 -> 50.8 | Improved |
| add boundary information to control propagation (ablation) | BFP with UAGs (ResNet-101) · PASCAL-Context (59 classes) | mIoU (%): 50.8 -> 52.8 | Improved |
| add multi-scale testing (ablation) | BFP (ResNet-101) · PASCAL-Context (59 classes) | mIoU (%): 52.8 -> 53.6 | Improved |
| replace DAGs with UAGs (ablation) | DAG-RNN style propagation · PASCAL-Context (59 classes), VGG-16 | mIoU (%): 42.6 -> 43.0 | No clear effect |
| replace DAGs with UAGs for speed at 960x720 (ablation) | dilated FCN · Inference speed, 960x720 | inference time (s): 56.97 -> 0.76 | Improved |
| replace DAGs with UAGs for speed at 480x360 (ablation) | dilated FCN · Inference speed, 480x360 | inference time (s): 17.92 -> 0.47 | Improved |
| filter BFP segmentation scores with domain transform (DT) | BFP · PASCAL-Context (59 classes) | mIoU (%): +0.7 | Improved |
| use BFP instead of best prior method EncNet | EncNet · PASCAL-Context (59 classes) | mIoU (%): 51.7 -> 53.6 | Improved |
| use BFP instead of Dense-Decoder | Dense-Decoder · CamVid | mIoU (%): 70.9 -> 74.1 | Improved |
| use BFP (ResNet-101) instead of DenseASPP (DenseNet-161) | DenseASPP · Cityscapes test | mIoU (%): 80.6 -> 81.4 | 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.
- PSANet — PSANet: Point-wise Spatial Attention Network for Scene Parsing (ECCV 2018) · better on 1 of 1 shared result
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
- Coupled Segmentation and Edge Learning via Dynamic Graph Propagation (NeurIPS 2021 · similarity 0.89)
- Improving Semantic Segmentation via Decoupled Body and Edge Supervision (ECCV 2020 · similarity 0.88)
- SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation (NeurIPS 2025 · similarity 0.87)
- Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure (NeurIPS 2024 · similarity 0.87)
- BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis (CVPR 2025 · similarity 0.87)
- Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling (CVPR 2024 · similarity 0.87)
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.
