Research map / Detection and segmentation / CNN features
DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion
Junjie Guo, Chenqiang Gao, Fangcen Liu, Deyu Meng, Xinbo Gao
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 Modality Competitive Query Selection (ablation) | DAMSDet baseline · M3FD | mAP50: 77.8 -> 78.9 | Improved |
| add Multispectral Deformable Cross-attention (ablation) | DAMSDet baseline · M3FD | mAP50: 77.8 -> 79.4 | Improved |
| add MCQS and MDCA together (ablation) | DAMSDet baseline · M3FD | mAP50: 77.8 -> 80.2 | Improved |
| use content query selection instead of learnable content query (ablation) | DAMSDet multimodal · M3FD | mAP50: 79.3 -> 80.2 | Improved |
| use content query selection in single-modality detection (ablation) | single-modality DETR branch · M3FD visible only | mAP50: 75.3 -> 75.7 | No clear effect |
| fuse infrared and visible with DAMSDet instead of CFT | CFT · M3FD | mAP50: 68.2 -> 80.2 | Improved |
| DAMSDet vs LRAF-Net on VEDAI overall mAP | DAMSDet · VEDAI | mAP: 59.1 -> 55.3 | Hurt |
| DAMSDet vs LRAF-Net on VEDAI mAP50 | DAMSDet · VEDAI | mAP50: 85.9 -> 91.5 | Improved |
| DAMSDet vs MS-DETR on near-saturated LLVIP mAP50 | DAMSDet · LLVIP | mAP50: 97.9 -> 97.9 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- MS-DETR — MS-DETR: Efficient DETR Training with Mixed Supervision (CVPR 2024) · better on 1 of 2 shared results
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
- DETR is Secretly a Multispectral Detector: Zero-Parameter Adaptation via Semantic Alignment (ECCV 2026 · similarity 0.88)
- Lightweight Transformer for Multi-Modal Object Detection (Student Abstract) (AAAI 2023 · similarity 0.86)
- MODA: The First Challenging Benchmark for Multispectral Object Detection in Aerial Images (AAAI 2026 · similarity 0.85)
- Efficient RGB-T Object Detection via Sparse Cross-Modality Fusion (ECCV 2026 · similarity 0.85)
- Target-Aware Dual Adversarial Learning and a Multi-Scenario Multi-Modality Benchmark To Fuse Infrared and Visible for Object Detection (CVPR 2022 · similarity 0.85)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · 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.
