Research map / Detection and segmentation / CNN features
OCNet: Object Context for Semantic Segmentation
Yuhui Yuan, Lang Huang, Jianyuan Guo, Chao Zhang, Xilin Chen, Jingdong Wang
Read the paperCheck your idea against 137,217 papers
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 Base-OC (ISA) object context module | Dilated ResNet-101 · Cityscapes val | mIoU: 75.90 -> 79.49 | Improved |
| use interlaced sparse self-attention instead of dense self-attention (ablation) | Base-OC · Cityscapes val | mIoU: 79.40 -> 79.49 | No clear effect |
| use Base-OC (ISA) instead of PPM (ablation) | Dilated ResNet-101 · Cityscapes val | mIoU: 78.50 -> 79.49 | Improved |
| use Base-OC (ISA) instead of PPM (ablation) | Dilated ResNet-50 · ADE20K val | mIoU: 41.50 -> 42.11 | Improved |
| use Base-OC (ISA) instead of ASPP (ablation) | Dilated ResNet-101 · Cityscapes val | mIoU: 79.10 -> 79.49 | Improved |
| apply global relation before local relation (ablation) | Base-OC (ISA) · Cityscapes val | mIoU: 79.10 -> 79.49 | Improved |
| use only global relation versus global plus local (ablation) | Base-OC (ISA) · Cityscapes val | mIoU: 78.9 -> 79.49 | Improved |
| use only local relation versus global plus local (ablation) | Base-OC (ISA) · Cityscapes val | mIoU: 77.2 -> 79.49 | Improved |
| set group numbers Ph=Pw=8 instead of 4 and 4 (ablation) | Base-OC (ISA) · Cityscapes val | mIoU: 78.97 -> 79.49 | Improved |
| add ASP-OC extension to Base-OC (ISA) (ablation) | OCNet · Cityscapes val | mIoU: 79.49 -> 80.01 | Improved |
| add Pyramid-OC extension to Base-OC (ISA) (ablation) | OCNet · Cityscapes val | mIoU: 79.49 -> 79.02 | Hurt |
| use Base-OC (ISA) instead of RCCA (ablation) | Dilated ResNet-101 · Cityscapes val | mIoU: 78.64 -> 79.49 | Improved |
Closest papers by meaning
- Object-Contextual Representations for Semantic Segmentation (ECCV 2020 · similarity 0.93)
- Self-Supervised Learning of Object Parts for Semantic Segmentation (CVPR 2022 · similarity 0.90)
- ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation (ICCV 2021 · similarity 0.89)
- Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation (CVPR 2025 · similarity 0.89)
- IDRNet: Intervention-Driven Relation Network for Semantic Segmentation (NeurIPS 2023 · similarity 0.89)
- Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure (NeurIPS 2024 · similarity 0.88)
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.
