Research map / Detection and segmentation / Open-set and few-shot detection
Scene Parsing via Integrated Classification Model and Variance-Based Regularization
Hengcan Shi, Hongliang Li, Qingbo Wu, Zichen Song
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 an integrated refinement classifier to PSPNet (ablation) | PSPNet · NYU Depth v2 | mIoU: 46.9 -> 50.3 | Improved |
| add variance-based regularization to the baseline (ablation) | PSPNet · NYU Depth v2 | mIoU: 46.9 -> 47.8 | Improved |
| combine integrated classification with variance-based regularization (ablation) | PSPNet · NYU Depth v2 | mIoU: 46.9 -> 50.7 | Improved |
| add DSN auxiliary classifiers (ablation) | PSPNet · NYU Depth v2 | mIoU: 46.9 -> 46.5 | Hurt |
| add more layers and parameters to the baseline (ablation) | PSPNet · NYU Depth v2 | pAcc.: 73.6 -> 73.3 | Hurt |
| use multiple binary rather than multinomial general classifiers (ablation) | integrated classification model · NYU Depth v2 | mIoU: 49.4 -> 50.7 | Improved |
| use the general-classification probability map as refinement input (ablation) | refinement classification network · NYU Depth v2 | mIoU: 46.9 -> 50.1 | Improved |
| also provide image features and the original image to refinement (ablation) | refinement classification network · NYU Depth v2 | mIoU: 50.1 -> 50.7 | Improved |
| set the variance-regularization weight to 0.2 (ablation) | integrated classification model · NYU Depth v2 | mIoU: λvbr=0: 50.3; λvbr=0.2: 50.7; λvbr=2: 49.7 | Mixed |
| use a three-layer refinement network with 1024-dimensional hidden layers (ablation) | integrated classification model · NYU Depth v2 | mIoU: 50.7 | Mixed |
| use the proposed integrated classifier and variance regularization | scene parsing models · PASCAL-Context | mIoU: 51.7 -> 52.6 | Improved |
| use the proposed integrated classifier and variance regularization | scene parsing models · SUN-RGBD | mIoU: 47.1 -> 50.6 | Improved |
Closest papers by meaning
- Deep Structured Scene Parsing by Learning With Image Descriptions (CVPR 2016 · similarity 0.86)
- FLOAT: Factorized Learning of Object Attributes for Improved Multi-Object Multi-Part Scene Parsing (CVPR 2022 · similarity 0.86)
- Sample and Filter: Nonparametric Scene Parsing via Efficient Filtering (CVPR 2016 · similarity 0.86)
- Hierarchical Scene Parsing by Weakly Supervised Learning with Image Descriptions (TPAMI 2018 · similarity 0.85)
- Weakly Supervised Scene Parsing with Point-Based Distance Metric Learning (AAAI 2019 · similarity 0.85)
- Temporal Pixel-Level Semantic Understanding Through the VSPW Dataset (TPAMI 2023 · 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.
