Research map / Detection and segmentation / CNN features
CoDeRNet: Selective Cross-Task Routing under Heterogeneous Supervision for Change Detection and Captioning
Eunki Cho, Hyeon Bae Kim, Seong Tae Kim
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes CoDeRNet, a unified change detection and captioning model for bi-temporal remote sensing images that uses selective cross-task routing to handle heterogeneous supervision between localization and description.
Problem
Joint change detection and captioning (CDC) on bi-temporal remote sensing images, where localization and language description receive heterogeneous supervision and task-specific communication between them is under-explored.
Approach
Selective cross-task routing that controls how detection and captioning branches exchange information under heterogeneous supervision, rather than relying only on shared representations or jointly optimized architectures.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add CoDeR routing to joint detection and captioning training (ablation) | CoDeRNet joint model · LEVIR-MCI | CIDEr-D: 136.18 -> 141.79 | Improved |
| add CoDeR routing to joint training (ablation) | CoDeRNet joint model · LEVIR-MCI | mIoU: 87.67 -> 87.79 | Improved |
| joint training without CoDeR versus captioning-only training (ablation) | captioning branch · LEVIR-MCI | CIDEr-D: 137.41 -> 136.18 | Hurt |
| joint training without CoDeR versus detection-only training (ablation) | detection branch · LEVIR-MCI | mIoU: 87.03 -> 87.67 | Improved |
| use bidirectional routing instead of cap to seg only (ablation) | CoDeR · LEVIR-MCI | CIDEr-D: 138.62 -> 141.79 | Improved |
| use bidirectional routing instead of seg to cap only (ablation) | CoDeR · LEVIR-MCI | CIDEr-D: 141.95 -> 141.79 | No clear effect |
| use decomposed mask (1-C_t)*C_s instead of sender reliability only (ablation) | CoDeR · LEVIR-MCI | CIDEr-D: 139.57 -> 141.79 | Improved |
| use decomposed mask instead of receiver need only (ablation) | CoDeR · LEVIR-MCI | CIDEr-D: 141.02 -> 141.79 | Improved |
| use decomposed mask instead of a single gate (ablation) | CoDeR · LEVIR-MCI | CIDEr-D: 138.19 -> 141.79 | Improved |
| use CoDeR instead of co-attention interaction (ablation) | CoDeRNet · LEVIR-MCI | CIDEr-D: 139.33 -> 141.79 | Improved |
| use CoDeR instead of co-attention for detection (ablation) | CoDeRNet · LEVIR-MCI | mIoU: 87.84 (Co-Attn) vs 87.79 (CoDeR) | No clear effect |
| use CoDeR instead of gated modulation (ablation) | CoDeRNet · LEVIR-MCI | CIDEr-D: 140.86 -> 141.79 | Improved |
Closest papers by meaning
- FM-ChangeNet: Learning Change through Pathwise Feature Transport (NeurIPS 2026 · similarity 0.87)
- RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-𝑁 Ranking (NeurIPS 2026 · similarity 0.87)
- Change3D: Revisiting Change Detection and Captioning from A Video Modeling Perspective (CVPR 2025 · similarity 0.85)
- The Change You Want To Detect: Semantic Change Detection In Earth Observation With Hybrid Data Generationf (CVPR 2025 · similarity 0.85)
- Revisiting Change Captioning from Self-supervised Global-Part Alignment (AAAI 2025 · similarity 0.85)
- Region-aware Difference Distilling with Attribute-guided Contrastive Regularization for Change Captioning (AAAI 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.
