Research map / Detection and segmentation / Open-set and few-shot detection
AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation
Chaofan Ma, Yuhuan Yang, Chen Ju, Fei Zhang, Ya Zhang, Yanfeng 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 |
|---|---|---|---|
| Use direct aggregation (all attributes in one sentence) instead of hierarchical (ablation) | AttrSeg RN101 · PASCAL-5i | mIoU: 49.1 -> 44.8 | Hurt |
| Use pre-aggregation instead of hierarchical (ablation) | AttrSeg RN101 · PASCAL-5i | mIoU: 49.1 -> 46.1 | Hurt |
| Use post-aggregation instead of hierarchical (ablation) | AttrSeg RN101 · PASCAL-5i | mIoU: 49.1 -> 46.7 | Hurt |
| Remove cross attention on images in the clustering module (ablation) | AttrSeg ViT-L · PASCAL-5i | mIoU: 56.4 -> 54.1 | Hurt |
| Remove cross attention on attributes (ablation) | AttrSeg ViT-L · PASCAL-5i | mIoU: 56.4 -> 54.6 | Hurt |
| Remove both cross attentions (ablation) | AttrSeg ViT-L · PASCAL-5i | mIoU: 56.4 -> 53.2 | Hurt |
| Remove the mixer (ablation) | AttrSeg ViT-L · PASCAL-5i | mIoU: 56.4 -> 55.7 | Hurt |
| Remove cross attention and mixer (slot attention only) (ablation) | AttrSeg ViT-L · PASCAL-5i | mIoU: 56.4 -> 52.9 | Hurt |
| Reduce aggregation stages from 4 to 2 with 15 attributes (ablation) | AttrSeg ViT-L · PASCAL-5i | mIoU: 56.4 -> 52.4 | Hurt |
| Increase aggregation stages from 4 to 5 with 15 attributes (ablation) | AttrSeg ViT-L · PASCAL-5i | mIoU: 56.4 -> 56.5 | No clear effect |
| Reduce number of input attributes from 15 to 5 (4 stages) (ablation) | AttrSeg ViT-L · PASCAL-5i | mIoU: 56.4 -> 51.1 | Hurt |
| Add inaccurate attributes to clean attributes (ablation) | AttrSeg · PASCAL-5i | mIoU: 59.5 -> 59.1 | No clear effect |
Closest papers by meaning
- Training-free Open-Vocabulary Semantic Segmentation via Diverse Prototype Construction and Sub-region Matching (AAAI 2025 · similarity 0.89)
- Exploring Simple Open-Vocabulary Semantic Segmentation (CVPR 2025 · similarity 0.89)
- CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation (CVPR 2024 · similarity 0.88)
- SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation (CVPR 2024 · similarity 0.88)
- Renovating Names in Open-Vocabulary Segmentation Benchmarks (NeurIPS 2024 · similarity 0.88)
- Excluding the Impossible for Open Vocabulary Semantic Segmentation (AAAI 2025 · 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.
