Research map / Detection and segmentation / Open-set and few-shot detection
SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding
Weitai Kang, Gaowen Liu, Mubarak Shah, Yan Yan
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 Triple Alignment to baseline (ablation) | Backbones + Encoder + Decoder · RefCOCOg-umd test | accuracy (%): 66.97 -> 75.75 | Improved |
| add multi-layer multi-task segmentation supervision (N=1) (ablation) | Backbones + Encoder + Decoder · RefCOCOg-umd test | accuracy (%): 66.97 -> 72.61 | Improved |
| increase segmentation queries from 1 to 5 (ablation) | MMDecoder · RefCOCOg-umd test | accuracy (%): 72.61 -> 76.21 | Improved |
| increase segmentation queries beyond 5 (7, 9) (ablation) | MMDecoder · RefCOCOg-umd test | accuracy (%): 76.21 -> 74.38 (N=7), 73.91 (N=9) | Hurt |
| combine Triple Alignment with multi-task decoder (ablation) | SegVG · RefCOCOg-umd test | accuracy (%): 76.21 -> 77.29 | Improved |
| keep multimodal encoder after Triple Alignment (ablation) | SegVG · RefCOCOg-umd test | accuracy (%): 76.65 -> 77.29 | Improved |
| include queries in Triple Alignment instead of text-vision bidirectional alignment only (ablation) | SegVG · RefCOCOg-umd test | accuracy (%): 76.37 -> 77.29 | Improved |
| add segmentation-derived confidence as focal factor on other losses (ablation) | SegVG · RefCOCOg-umd test | accuracy (%): 76.83 -> 77.29 | Improved |
| use bbox2seg masks instead of pseudo segmentation labels from a RES model (ablation) | SegVG · ReferItGame test | accuracy (%): 73.76 -> 75.06 | Improved |
| choose which segmentation query yields the confidence score (ablation) | SegVG · RefCOCOg-umd test | AP50: 84.57 to 84.78 across queries | No clear effect |
| raise confidence threshold at inference | SegVG · RefCOCOg-umd test | accuracy and mean IoU | Improved |
Closest papers by meaning
- GroundVLP: Harnessing Zero-Shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detection (AAAI 2024 · similarity 0.89)
- SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion (NeurIPS 2024 · similarity 0.88)
- Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints (AAAI 2025 · similarity 0.87)
- VGent: Visual Grounding via Modular Design for Disentangling Reasoning and Prediction (CVPR 2026 · similarity 0.87)
- Mask Grounding for Referring Image Segmentation (CVPR 2024 · similarity 0.87)
- Seg-ReSearch: Segmentation with Interleaved Reasoning and External Search (ICML 2026 · similarity 0.87)
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.
