Research map / Vision-language and multimodal / Cross-modal learning
Encoder Fusion Network With Co-Attention Embedding for Referring Image Segmentation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 decoder fusion with encoder fusion (ablation) | CEFNet · UNC val | overall IoU: 52.86 -> 55.87 | Helped |
| Add vanilla co-attention to EFN (ablation) | CEFNet · UNC val | overall IoU: 55.87 -> 59.65 | Helped |
| Add asymmetric co-attention to EFN (ablation) | CEFNet · UNC val | overall IoU: 55.87 -> 60.09 | Helped |
| Add BEM to EFN with vanilla co-attention (ablation) | CEFNet · UNC val | overall IoU: 59.65 -> 62.53 | Helped |
| Add BEM to EFN with asymmetric co-attention (ablation) | CEFNet · UNC val | overall IoU: 60.09 -> 62.76 | Helped |
| Use ACM instead of VCM in the full model | CEFNet · UNC+ testB | IoU: 43.50 -> 43.01 | Hurt |
| Train on combined UNC, UNC+ and G-Ref data | CEFNet · UNC val | IoU: 62.76 -> 68.97 | Helped |
| Use ACM instead of VCM in the full model | CEFNet · UNC val | IoU: 62.53 -> 62.76 | Helped |
| Use ACM instead of VCM in the full model | CEFNet · G-Ref val | IoU: 51.22 -> 51.93 | Helped |
Closest papers by meaning
- Cross-Modal Self-Attention Network for Referring Image Segmentation (CVPR 2019 · similarity 0.90)
- LQMFormer: Language-aware Query Mask Transformer for Referring Image Segmentation (CVPR 2024 · similarity 0.88)
- Image Fusion via Vision-Language Model (ICML 2024 · similarity 0.85)
- MRFS: Mutually Reinforcing Image Fusion and Segmentation (CVPR 2024 · similarity 0.84)
- Keep the Balance: A Parameter-Efficient Symmetrical Framework for RGB+X Semantic Segmentation (CVPR 2025 · similarity 0.84)
- Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective (NeurIPS 2024 · similarity 0.84)
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.