Research map / Detection and segmentation / Open-set and few-shot detection
Scene Parsing Through ADE20K Dataset
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 the Cascade Segmentation Module to DilatedNet | DilatedNet · SceneParse150 validation | Mean IoU: 0.3231 -> 0.3490 | Helped |
| Add the Cascade Segmentation Module to DilatedNet | DilatedNet · SceneParse150 validation | Pixel accuracy: 73.55% -> 74.52% | Helped |
| Add the Cascade Segmentation Module to DilatedNet | DilatedNet · SceneParse150 validation | Mean accuracy: 44.59% -> 45.38% | Helped |
| Add the Cascade Segmentation Module to DilatedNet | DilatedNet · SceneParse150 validation | Weighted IoU: 0.6014 -> 0.6108 | Helped |
| Add the Cascade Segmentation Module to DilatedNet | DilatedNet · SceneParse150 validation, discrete object classes | Mean IoU: 0.3080 -> 0.3401 | Helped |
| Add the Cascade Segmentation Module to DilatedNet | DilatedNet · SceneParse150 validation, stuff classes | Mean IoU: 0.3729 -> 0.3779 | Helped |
| Add the Cascade Segmentation Module to SegNet | SegNet · SceneParse150 validation | Mean IoU: 0.2164 -> 0.2751 | Helped |
| Add the Cascade Segmentation Module to SegNet | SegNet · SceneParse150 validation, discrete object classes | Mean IoU: 0.1894 -> 0.2600 | Helped |
Closest papers by meaning
- FLOAT: Factorized Learning of Object Attributes for Improved Multi-Object Multi-Part Scene Parsing (CVPR 2022 · similarity 0.88)
- VSPW: A Large-scale Dataset for Video Scene Parsing in the Wild (CVPR 2021 · similarity 0.87)
- Pyramid Scene Parsing Network (CVPR 2017 · similarity 0.87)
- The Scene Language: Representing Scenes with Programs, Words, and Embeddings (CVPR 2025 · similarity 0.84)
- OW-VAP: Visual Attribute Parsing for Open World Object Detection (ICML 2025 · similarity 0.84)
- Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure (NeurIPS 2024 · similarity 0.84)
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.