Research map / Detection and segmentation / Weakly supervised detection and segmentation
A Simple Framework for Text-Supervised Semantic Segmentation
Muyang Yi, Quan Cui, Hao Wu, Cheng Yang, Osamu Yoshie, Hongtao Lu
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 |
|---|---|---|---|
| Replace dense alignment with locality-driven alignment (LoDA) (ablation) | SimSeg with ViT-S · PASCAL VOC 2012 | mIoU: 19.1 -> 56.6 | Improved |
| Replace dense alignment with locality-driven alignment (LoDA) (ablation) | SimSeg with ViT-S · PASCAL Context | mIoU: 11.0 -> 25.8 | Improved |
| Replace dense alignment with locality-driven alignment (LoDA) (ablation) | SimSeg with ViT-S · COCO-Stuff | mIoU: 12.5 -> 27.2 | Improved |
| Use ViT-B instead of ViT-S as the backbone | SimSeg with LoDA · PASCAL VOC 2012 | mIoU: 56.6 -> 57.4 | Improved |
| Use ViT-B instead of ViT-S as the backbone | SimSeg with LoDA · PASCAL Context | mIoU: 25.8 -> 26.2 | Improved |
| Use ViT-B instead of ViT-S as the backbone | SimSeg with LoDA · COCO-Stuff | mIoU: 27.2 -> 29.7 | Improved |
| Set the potential-class threshold to 1.5×σ instead of the default 1.0×σ (ablation) | SimSeg with ViT-S · PASCAL VOC 2012 | mIoU: 56.6 -> 57.8 | Improved |
| Set the potential-class threshold to 0.25×σ (ablation) | SimSeg with ViT-S · PASCAL VOC 2012 | mIoU: 56.6 -> 51.0 | Hurt |
| Set the potential-class threshold to 0.5×σ (ablation) | SimSeg with ViT-S · PASCAL VOC 2012 | mIoU: 56.6 -> 53.0 | Hurt |
| Set the potential-class threshold to 0.75×σ (ablation) | SimSeg with ViT-S · PASCAL VOC 2012 | mIoU: 56.6 -> 55.1 | Hurt |
| Set the potential-class threshold to 1.25×σ (ablation) | SimSeg with ViT-S · PASCAL VOC 2012 | mIoU: 56.6 -> 57.1 | Improved |
| Set the potential-class threshold to 1.75×σ (ablation) | SimSeg with ViT-S · PASCAL VOC 2012 | mIoU: 56.6 -> 56.4 | Hurt |
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.
- GroupViT — GroupViT: Semantic Segmentation Emerges From Text Supervision (CVPR 2022) · better on 3 of 3 shared results
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
- Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation (CVPR 2024 · similarity 0.91)
- CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation (CVPR 2023 · similarity 0.90)
- Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation (CVPR 2025 · similarity 0.90)
- Unveiling the Knowledge of CLIP for Training-Free Open-Vocabulary Semantic Segmentation (AAAI 2025 · similarity 0.88)
- Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP (AAAI 2025 · similarity 0.88)
- CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation (CVPR 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.
