Research map / Detection and segmentation / Open-set and few-shot detection
Beyond One-to-One: Rethinking the Referring Image Segmentation
Yutao Hu, Qixiong Wang, Wenqi Shao, Enze Xie, Zhenguo Li, Jungong Han, Ping Luo
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 the image-to-text decoder (L_sim and L_con) (ablation) | DMMI · G-Ref val (U) | oIoU: 61.76 -> 63.46 | Improved |
| add similarity loss L_sim for text reconstruction (ablation) | DMMI · Ref-ZOM test | oIoU / Acc: 65.77 -> 67.25 oIoU; 83.91 -> 85.55 Acc | Improved |
| add contrastive loss L_con (ablation) | DMMI · Ref-ZOM test | oIoU / Acc: 65.77 -> 66.36 oIoU; 83.91 -> 84.73 Acc | Improved |
| combine L_sim and L_con (ablation) | DMMI · G-Ref val (U) | oIoU: 62.47 -> 63.46 | Improved |
| add multi-scale local-region interaction in MBA (ablation) | DMMI · Ref-ZOM test | oIoU: 67.31 -> 68.77 | Improved |
| add bi-direction (image-to-text alignment) in MBA (ablation) | DMMI · Ref-ZOM test | oIoU: 67.52 -> 68.77 | Improved |
| replace LAVT with DMMI (Swin-B) | referring segmentation · Ref-ZOM test | oIoU: 64.45 -> 68.77 | Improved |
| replace LAVT with DMMI (Swin-B) | referring segmentation · RefCOCO val | oIoU: 72.73 -> 74.13 | Improved |
| train on Ref-ZOM with one-to-many and one-to-zero samples | DMMI · Zero-shot Cityscapes | qualitative | Improved |
Closest papers by meaning
- Referring Image Segmentation via Cross-Modal Progressive Comprehension (CVPR 2020 · similarity 0.91)
- Boosting Weakly Supervised Referring Image Segmentation via Progressive Comprehension (NeurIPS 2024 · similarity 0.89)
- Mask Grounding for Referring Image Segmentation (CVPR 2024 · similarity 0.88)
- OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling (NeurIPS 2024 · similarity 0.88)
- Referencing Where to Focus: Improving Visual Grounding with Referential Query (NeurIPS 2024 · similarity 0.88)
- Hybrid Global-Local Representation with Augmented Spatial Guidance for Zero-Shot Referring Image Segmentation (CVPR 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.
