Research map / Detection and segmentation / CNN features
Variational Context-Deformable ConvNets for Indoor Scene Parsing
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 |
|---|---|---|---|
| Replace standard convolution with VCD modules | ACNet · SUN RGB-D | mIoU: 48.1 -> 51.2 | Helped |
| Replace standard convolution with VCD modules | RedNet · SUN RGB-D | mIoU: 47.8 -> 50.3 | Helped |
| Replace standard convolution with VCD modules | ACNet · NYUv2 | mIoU: 48.3 -> 51.9 | Helped |
| Replace standard convolution with VCD modules | RedNet · NYUv2 | mIoU: 47.2 -> 50.7 | Helped |
| Replace the last four branches of stage 4 with VCD modules | HRNetV2-W48 · Cityscapes test | mIoU: 81.6 -> 82.3 | Helped |
| Add structured Gaussian-kernel context adaptation (ablation) | DeeplabV3 · NYUv2 | mIoU: 43.8 -> 46.0 | Helped |
| Add deformable convolution to VCD (ablation) | VCD · NYUv2 | mIoU: 46.0 -> 46.4 | Helped |
| Add stochastic Bayesian modeling to VCD trained with DCN (ablation) | VCD+DCN · NYUv2 | mIoU: 46.4 -> 47.1 | Helped |
Closest papers by meaning
- Locality-Sensitive Deconvolution Networks With Gated Fusion for RGB-D Indoor Semantic Segmentation (CVPR 2017 · similarity 0.87)
- Deformable ConvNets V2: More Deformable, Better Results (CVPR 2019 · similarity 0.85)
- Multi-Scale Representations by Varying Window Attention for Semantic Segmentation (ICLR 2024 · similarity 0.84)
- PDDM: Pseudo Depth Diffusion Model for RGB-PD Semantic Segmentation Based in Complex Indoor Scenes (AAAI 2025 · similarity 0.83)
- Explore In-Context Segmentation via Latent Diffusion Models (AAAI 2025 · similarity 0.83)
- OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation (CVPR 2024 · 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.