Research map / Detection and segmentation / CNN features
FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small-Object Detection
Aiwen Liu, Chengguang Zhu, Gang Wang, Dandan Zhu, Haodong Lin, Yan Wang, Huiyu Zhou, Zhengyi Pan
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 FSDC-DETR frequency-spatial modules (DBFSAF, SFS-FF, FSD-Down) | DEIMv2-L · VisDrone-DET2019 test | AP: 24.7 -> 31.1 | Improved |
| add FSDC-DETR frequency-spatial modules | DEIMv2-L · AITODv2 test | AP: 25.7 -> 32.3 | Improved |
| add FSDC-DETR frequency-spatial modules | DEIMv2-L · VisDrone-DET2019 test | APs: 14.2 -> 21.0 | Improved |
| add FSDC-DETR frequency-spatial modules | DEIMv2-L · AITODv2 test | APs: 24.4 -> 31.3 | Improved |
| add DBFSAF (ablation) | DEIMv2-L · VisDrone-DET2019 test | AP: 24.7 -> 29.7 | Improved |
| add SFS-FF alone (ablation) | DEIMv2-L · VisDrone-DET2019 test | AP: 24.7 -> 25.9 | Improved |
| add FSD-Down alone (ablation) | DEIMv2-L · VisDrone-DET2019 test | AP: 24.7 -> 25.4 | Improved |
| add SFS-FF on top of DBFSAF (ablation) | DBFSAF model · VisDrone-DET2019 test | AP: 29.7 -> 30.3 | Improved |
| add FSD-Down on top of DBFSAF + SFS-FF (ablation) | DBFSAF + SFS-FF · VisDrone-DET2019 test | AP: 30.3 -> 31.1 | Improved |
| add FSD-Down on top of DBFSAF only (ablation) | DBFSAF model · VisDrone-DET2019 test | AP: 29.7 -> 30.0 | Improved |
| set DBFSAF partial ratio gamma to 0.5 instead of 0 (ablation) | FSDC-DETR · VisDrone-DET2019 test | AP: 29.7 -> 31.1 | Improved |
| set gamma to 0.5 instead of 1 (ablation) | FSDC-DETR · VisDrone-DET2019 test | AP: 30.0 -> 31.1 | Improved |
Closest papers by meaning
- CF-DETR: Coarse-to-Fine Transformers for End-to-End Object Detection (AAAI 2022 · similarity 0.87)
- DyFCLT: Dynamic Frequency-Decoupled Cross-Modal Learning Transformer for Multimodal Tiny Object Detection (CVPR 2026 · similarity 0.87)
- FD2-Net: Frequency-Driven Feature Decomposition Network for Infrared-Visible Object Detection (AAAI 2025 · similarity 0.87)
- HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection (AAAI 2025 · similarity 0.86)
- FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network (NeurIPS 2025 · similarity 0.86)
- Frequency Dynamic Convolution for Dense Image Prediction (CVPR 2025 · similarity 0.86)
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.
