Research map / Vision-language and multimodal / Cross-modal learning
DGKAN: Dual-branch Graph Kolmogorov-Arnold Network for Unsupervised Multimodal Change Detection
Tongfei Liu, Jianjian Xu, Tao Lei, Yingbo Wang, Xiaogang Du, Zhiyong Lv
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 KAN path in parallel to GCN in GKAN (versus removing it) (ablation) | DGKAN · MCD datasets #1-#5 | Ka | Improved |
| use KAN branch instead of MLP branch in GKAN (ablation) | DGKAN · MCD datasets #1-#5 | Ka: +8.1% average Ka | Improved |
| add covariance structural commonality loss (CSCL) to reconstruction loss (ablation) | DGKAN · MCD datasets #1-#5 | Ka | Improved |
| use GKAN (GCN + KAN) instead of GCN alone | DGKAN · Dataset #5 compute | inference time: 1.59s -> 4.19s; FLOPs 21.76M -> 65.28M | Hurt |
| use DGKAN versus best prior unsupervised methods | DGKAN · Datasets #1-#5 | Ka: #2 0.831 -> 0.838; #5 0.687 (LPEM) vs 0.688; ties on #1 | Mixed |
| vary SLIC superpixel number Pn and compactness Pc (ablation) | DGKAN · Datasets #1-#5 | Ka | Mixed |
Closest papers by meaning
- The Change You Want To Detect: Semantic Change Detection In Earth Observation With Hybrid Data Generationf (CVPR 2025 · similarity 0.83)
- FM-ChangeNet: Learning Change through Pathwise Feature Transport (NeurIPS 2026 · similarity 0.83)
- Feature Spectrum Learning for Remote Sensing Change Detection (CVPR 2025 · similarity 0.83)
- Towards Generalizable Scene Change Detection (CVPR 2025 · similarity 0.83)
- LDS2AE: Local Diffusion Shared-Specific Autoencoder for Multimodal Remote Sensing Image Classification with Arbitrary Missing Modalities (AAAI 2024 · similarity 0.83)
- UniChange: Unifying Change Detection with Multimodal Large Language Model (CVPR 2026 · similarity 0.83)
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.
