Research map / Vision-language and multimodal / Human and embodied modeling
Vision-Language Transformer and Query Generation for Referring Segmentation
Henghui Ding, Chang Liu, Suchen Wang, Xudong Jiang
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 transformer, QGM and QBM in place of seven conv layers (ablation) | VLT · RefCOCO+ test B | IoU: 44.28 -> 49.36 | Improved |
| add transformer, QGM and QBM in place of seven conv layers (ablation) | VLT · RefCOCO+ test B | Pr@0.5: 49.54 -> 55.84 | Improved |
| generate queries with Query Generation Module instead of word features (ablation) | VLT · RefCOCO+ test B | IoU: 45.05 -> 49.36 | Improved |
| generate queries with Query Generation Module instead of fixed learned queries (ablation) | VLT · RefCOCO+ test B | IoU: 42.99 -> 49.36 | Improved |
| increase number of queries from 1 to 16 (ablation) | VLT · RefCOCO+ test B | IoU: 44.83 -> 49.36 | Improved |
| increase number of queries from 16 to 32 (ablation) | VLT · RefCOCO+ test B | IoU: 49.36 -> 49.27 | No clear effect |
| increase number of queries from 2 to 4 (ablation) | VLT · RefCOCO+ test B | IoU: 47.07 -> 46.79; Pr@0.5 52.85 -> 53.06 | Mixed |
| add Query Balance Module (ablation) | VLT with 16 queries · RefCOCO+ test B | IoU: 48.94 -> 49.36 | Improved |
| add Query Balance Module (ablation) | VLT with 16 queries · RefCOCO+ test B | Pr@0.9: 12.99 -> 10.76 | Mixed |
| VLT vs best prior method CGAN | VLT · RefCOCO+ test B | IoU: 44.06 -> 49.36 | Improved |
| VLT vs best prior method CGAN | VLT · RefCOCO+ test B | IoU (RefCOCO val): 64.86 -> 65.65 | Improved |
| VLT vs best prior method CGAN | VLT · RefCOCO+ test B | IoU (G-Ref test UMD): 51.69 -> 56.65 | Improved |
Closest papers by meaning
- VLT: Vision-Language Transformer and Query Generation for Referring Segmentation (TPAMI 2022 · similarity 0.95)
- LQMFormer: Language-aware Query Mask Transformer for Referring Image Segmentation (CVPR 2024 · similarity 0.92)
- Locate Then Segment: A Strong Pipeline for Referring Image Segmentation (CVPR 2021 · similarity 0.92)
- Language-Aware Vision Transformer for Referring Segmentation (TPAMI 2024 · similarity 0.91)
- Mask Grounding for Referring Image Segmentation (CVPR 2024 · similarity 0.89)
- SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction (NeurIPS 2026 · 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.
