Research map / Detection and segmentation / CNN features
Locality-Sensitive Deconvolution Networks With Gated Fusion for RGB-D Indoor Semantic Segmentation
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 |
|---|---|---|---|
| Add locality-sensitive operations to RGB DeconvNet (ablation) | RGB DeconvNet · NYU-Depth v2 | mean IOU: 37.4 -> 40.5 | Helped |
| Add locality-sensitive operations to HHA DeconvNet (ablation) | HHA DeconvNet · NYU-Depth v2 | mean IOU: 33.4 -> 38.7 | Helped |
| Add gated fusion instead of sum fusion (ablation) | RGB-HHA + DeconvNet · NYU-Depth v2 | mean IOU: 42.7 -> 43.2 | Helped |
| Add gated fusion instead of product fusion (ablation) | RGB-HHA + DeconvNet · NYU-Depth v2 | mean IOU: 40.6 -> 43.2 | Helped |
| Add gated fusion instead of Dempster-Shafer fusion (ablation) | RGB-HHA + DeconvNet · NYU-Depth v2 | mean IOU: 42.8 -> 43.2 | Helped |
| Add gated fusion instead of sum fusion (ablation) | RGB-HHA + LS-DeconvNet · NYU-Depth v2 | mean IOU: 45.3 -> 45.9 | Helped |
| Add gated fusion instead of product fusion (ablation) | RGB-HHA + LS-DeconvNet · NYU-Depth v2 | mean IOU: 44.9 -> 45.9 | Helped |
| Add gated fusion instead of Dempster-Shafer fusion (ablation) | RGB-HHA + LS-DeconvNet · NYU-Depth v2 | mean IOU: 45.8 -> 45.9 | Helped |
Closest papers by meaning
- Discriminative Multi-Modal Feature Fusion for RGBD Indoor Scene Recognition (CVPR 2016 · similarity 0.88)
- DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation (ICLR 2024 · similarity 0.87)
- Variational Context-Deformable ConvNets for Indoor Scene Parsing (CVPR 2020 · similarity 0.87)
- Geometric Exploitation for Indoor Panoramic Semantic Segmentation (NeurIPS 2024 · similarity 0.86)
- PDDM: Pseudo Depth Diffusion Model for RGB-PD Semantic Segmentation Based in Complex Indoor Scenes (AAAI 2025 · similarity 0.86)
- DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation (CVPR 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.