Research map / Detection and segmentation / CNN features
Progressive Mirror Detection
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use Progressive Mirror Detection instead of MirrorNet | mirror detection · MSD | Fβ: 0.857 -> 0.898 | Helped |
| Use Progressive Mirror Detection instead of the strongest baseline | mirror detection · ADE20K | Fβ: 0.722 -> 0.743 | Helped |
| Use Progressive Mirror Detection instead of the strongest baseline | mirror detection · COCO-Stuff | Fβ: 0.651 -> 0.659 | Helped |
| Use Progressive Mirror Detection instead of the strongest baseline | mirror detection · MINC | Fβ: 0.608 -> 0.621 | Helped |
| Use Progressive Mirror Detection instead of the strongest baseline | mirror detection · NYUD-V2 | Fβ: 0.706 -> 0.726 | Helped |
| Use Progressive Mirror Detection instead of the strongest baseline | mirror detection · Pascal-Context | Fβ: 0.557 -> 0.560 | Helped |
| Use Progressive Mirror Detection instead of the strongest baseline | mirror detection · SUNRGBD | Fβ: 0.641 -> 0.657 | Helped |
| Add RCCL to the Basic network (ablation) | Basic mirror detector · MSD | Fβ: 0.859 -> 0.866 | Helped |
| Add EDF to the Basic network (ablation) | Basic mirror detector · MSD | Fβ: 0.859 -> 0.864 | Helped |
| Use only a single low-level edge extractor instead of EDF's low- and high-level extractors (ablation) | Basic mirror detector · MSD | Fβ: 0.859 -> 0.858 | Hurt |
| Add EDF and RCCL (ablation) | Basic mirror detector · MSD | Fβ: 0.859 -> 0.889 | Helped |
| Add the refinement module to Basic + EDF + RCCL (ablation) | mirror detector · MSD | Fβ: 0.889 -> 0.898 | Helped |
Closest papers by meaning
- ZOOM: Learning Video Mirror Detection with Extremely-Weak Supervision (AAAI 2024 · similarity 0.92)
- Detect Any Mirrors: Boosting Learning Reliability on Large-Scale Unlabeled Data with an Iterative Data Engine (CVPR 2025 · similarity 0.91)
- Weakly-Supervised Mirror Detection via Scribble Annotations (AAAI 2024 · similarity 0.89)
- Effective Video Mirror Detection with Inconsistent Motion Cues (CVPR 2024 · similarity 0.88)
- MIRROR: Make Your Object-Level Multi-View Generation More Consistent with Training-Free Rectification (ICML 2025 · similarity 0.85)
- MirrorVerse: Pushing Diffusion Models to Realistically Reflect the World (CVPR 2025 · similarity 0.83)
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.