Research map / Detection and segmentation / Open-set and few-shot detection
HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation
Read the paperCheck 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 |
|---|---|---|---|
| Use hierarchical grouping instead of flat whole-level grouping | HGFormer vs Mask2Former · ACDC all (Cityscapes train), ResNet-50 | mIoU: 49.8 -> 53.0 | Helped |
| Use hierarchical grouping instead of flat whole-level grouping | HGFormer vs Mask2Former · Cityscapes train to BDD, Mapillary, GTAV, Synthia average; ResNet-50 | mIoU: 46.9 -> 48.4 | Helped |
| Use hierarchical grouping instead of flat whole-level grouping | HGFormer vs Mask2Former · Mapillary train to GTAV, Synthia, Cityscapes, BDD average; ResNet-50 | mIoU: 53.9 -> 55.7 | Helped |
| Use hierarchical grouping instead of flat whole-level grouping | HGFormer vs Mask2Former · Cityscapes-C level 5 average; Swin-T | mIoU: 41.6 -> 43.9 | Helped |
| Use 4 rather than 1 part-level grouping iteration (ablation) | HGFormer · Six-dataset average (Cityscapes train) | mIoU: 55.7 -> 56.3 | Helped |
| Increase part-level grouping iterations from 4 to 6 (ablation) | HGFormer · Six-dataset average (Cityscapes train) | mIoU: 56.3 -> 55.6 | Hurt |
| Add part-level mask classification to whole-level classification (ablation) | HGFormer · Five target datasets average (Cityscapes train) | mIoU: 51.1 -> 52.4 | Helped |
| Add whole-level mask classification to part-level classification (ablation) | HGFormer · Five target datasets average (Cityscapes train) | mIoU: 52.1 -> 52.4 | Helped |
| Remove whole-level grouping during training (ablation) | HGFormer part-level classifier · Part-level iteration performance | mIoU | Helped |
Closest papers by meaning
- Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure (NeurIPS 2024 · similarity 0.88)
- Learning Hierarchical Image Segmentation For Recognition and By Recognition (ICLR 2024 · similarity 0.88)
- Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincare Ball (CVPR 2024 · similarity 0.87)
- Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective (NeurIPS 2024 · similarity 0.87)
- Collaborating Foundation Models for Domain Generalized Semantic Segmentation (CVPR 2024 · similarity 0.87)
- SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation (CVPR 2024 · similarity 0.86)
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.