Research map / Detection and segmentation / Open-set and few-shot detection
PEARL: Geometry Aligns Semantics for Training-Free Open-Vocabulary Semantic Segmentation
Gensheng Pei, Xiruo Jiang, Xinhao Cai, Tao Chen, Yazhou Yao, Byeungwoo Jeon
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 Procrustes alignment (PA) to vanilla CLIP (ablation) | CLIP ViT-B/16 · 8-benchmark average | mIoU: 13.8 -> 40.6 | Improved |
| add text-aware Laplacian propagation (TLP) to vanilla CLIP (ablation) | CLIP ViT-B/16 · 8-benchmark average | mIoU: 13.8 -> 29.3 | Improved |
| add TLP on top of PA (ablation) | PEARL · 8-benchmark average | mIoU: 40.6 -> 43.2 | Improved |
| add TLP plug-in to SCLIP (ablation) | SCLIP · 8-benchmark average | mIoU: 38.2 -> 42.2 | Improved |
| add TLP plug-in to NACLIP (ablation) | NACLIP · 8-benchmark average | mIoU: 39.4 -> 42.3 | Improved |
| add TLP plug-in to SFP (ablation) | SFP · 8-benchmark average | mIoU: 39.6 -> 41.5 | Improved |
| increase input short side from 224 to 336 px (ablation) | PEARL · 8-benchmark average | mIoU: 40.4 -> 42.7 | Improved |
| use larger CLIP ViT-L/14 backbone instead of ViT-B/16 (ablation) | PEARL · V21/PC59/Stuff/ADE | mIoU: ADE 20.7 with L/14 (higher than B/16 19.4) | Mixed |
| use PEARL instead of NACLIP | NACLIP · Object and ADE benchmarks vs best methods | mIoU: avg 39.4 -> 43.2 | Mixed |
| add PEARL's alignment and propagation (ablation) | PEARL · Pascal VOC 21 | mIoU: 59.2 -> 64.1 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ClearCLIP — ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference (ECCV 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models (CVPR 2024 · similarity 0.91)
- Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation (CVPR 2024 · similarity 0.90)
- Training-free Open-Vocabulary Semantic Segmentation via Diverse Prototype Construction and Sub-region Matching (AAAI 2025 · similarity 0.89)
- LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation (CVPR 2025 · similarity 0.89)
- Image-to-Image Matching via Foundation Models: A New Perspective for Open-Vocabulary Semantic Segmentation (CVPR 2024 · similarity 0.89)
- Relationship Prompt Learning is Enough for Open-Vocabulary Semantic Segmentation (NeurIPS 2024 · similarity 0.89)
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.
