Research map / Architectures and efficiency / CNN design
Convolutional Oriented Boundaries
Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Pablo Arbeláez, Luc Van Gool
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 trained orientations and drop globalization (final COB system) (ablation) | COB (ResNet50) · PASCAL Context VOC val | boundary and region F-measure | Improved |
| add globalization on top of trained orientations (ablation) | COB · PASCAL Context VOC val | boundary and region quality | Hurt |
| replace VGGNet base with ResNet50 (ablation) | COB · PASCAL Context VOC val | boundary and region quality | Improved |
| use trained orientations instead of local gradient orientation estimation | COB · Contour orientation (8 bins) | area under accuracy curve (%): 41.2 -> 58.6 | Improved |
| use sparse boundaries representation for OWT and UCM | MCG-HED · PASCAL Context timing | OWT and UCM time (s): 11.58 -> 1.63 | Improved |
| remove globalization, compute three scales in one pass, add orientations | Fast UCMs · PASCAL Context timing | total time (s): 24.37 -> 0.79 | Improved |
Closest papers by meaning
- Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks (TPAMI 2017 · similarity 0.99)
- Learning on the Edge: Investigating Boundary Filters in CNNs (IJCV 2019 · similarity 0.88)
- Occlusion Boundary Detection via Deep Exploration of Context (CVPR 2016 · similarity 0.87)
- Learning to Predict Crisp Boundaries (ECCV 2018 · similarity 0.87)
- Devil Is in the Edges: Learning Semantic Boundaries From Noisy Annotations (CVPR 2019 · similarity 0.87)
- Semantic Segmentation With Boundary Neural Fields (CVPR 2016 · similarity 0.86)
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.
