Research map / Detection and segmentation / CNN features
Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation
Jinyuan Liu, Zhu Liu, Guanyao Wu, Long Ma, Risheng Liu, Wei Zhong, Zhongxuan Luo, Xin Fan
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 direct feature aggregation (concatenate) with full hierarchical interactive attention (ablation) | SegMiF · MFNet segmentation | mIoU: 52.7 -> 56.1 | Improved |
| replace direct feature aggregation (concatenate) with full HIA (ablation) | SegMiF · FMB segmentation | mIoU: 51.3 -> 54.8 | Improved |
| add semantic-oriented attention module (SoAM) to HIA (ablation) | SegMiF HIA · FMB segmentation | mIoU: 52.3 -> 54.8 | Improved |
| add modality-oriented attention module (MoAM) to HIA (ablation) | SegMiF HIA · MFNet segmentation | mIoU: 53.4 -> 56.1 | Improved |
| use attention variants M1 (neither SoAM nor MoAM) versus aggregation (ablation) | SegMiF HIA · MFNet segmentation | mIoU: 52.7 -> 51.9 | No clear effect |
| use dynamic weighting factor instead of other multi-task strategies (ablation) | SegMiF training · MFNet and FMB | fusion and segmentation quality | Improved |
| joint fusion and segmentation with interactive features versus best prior method | SegMiF · FMB segmentation | mIoU: 50.9 -> 54.8 | Improved |
| SegMiF versus dual-stream and fusion baselines on mAcc | SegMiF · MFNet segmentation | mAcc: 75.4 (LASNet) vs 74.8 | Mixed |
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.
- GMNet — GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild (ECCV 2020) · better on 1 of 1 shared result
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
- MRFS: Mutually Reinforcing Image Fusion and Segmentation (CVPR 2024 · similarity 0.88)
- Keep the Balance: A Parameter-Efficient Symmetrical Framework for RGB+X Semantic Segmentation (CVPR 2025 · similarity 0.86)
- Rethinking Interactive Image Segmentation with Low Latency High Quality and Diverse Prompts (CVPR 2024 · similarity 0.85)
- Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond (CVPR 2025 · similarity 0.85)
- One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion (CVPR 2025 · similarity 0.85)
- Generative Map Priors for Collaborative BEV Semantic Segmentation (CVPR 2025 · similarity 0.85)
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.
