Research map / Detection and segmentation / CNN features
Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling
Shiji Zhao, Shukun Xiong, Maoxun Yuan, Yao Huang, Ranjie Duan, Qing Guo, Jiansheng Chen, Haibin Duan, Xingxing Wei
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 KGAT to MTD adversarial training | MTD on Faster R-CNN · M3FD | mAP50 (Avg): 49.9 -> 60.5 | Improved |
| add KGAT to SALC adversarial training | SALC on DINO · M3FD | mAP50 (Avg): 63.2 -> 70.8 | Improved |
| add KGAT to SALC adversarial training | SALC on YOLO-v8 · M3FD | mAP50 (Avg): 58.2 -> 66.5 | Improved |
| add KGAT to RobustDet | RobustDet on SSD · M3FD | mAP50 (Avg): 46.8 -> 50.0 | Improved |
| add KGAT to MTD | MTD on SSD · M3FD | mAP50 (Avg): 37.3 -> 43.2; clean 50.3 -> 56.1 | Improved |
| add KGAT to RobustDet | RobustDet on SSD · M3FD | mAP50 under A_mtd attack: A_mtd 37.9 -> 37.6 | Mixed |
| add KGAT to SALC | SALC on Faster R-CNN · FLIR-ADAS | mAP50 (Avg): 49.6 -> 54.7 | Improved |
| add KGAT to SALC | SALC on YOLO-v8 · FLIR-ADAS | mAP50 (Avg): 47.1 -> 53.4 | Improved |
| add KGAT to RobustDet | RobustDet on SSD · FLIR-ADAS | mAP50 (Avg): 43.5 -> 45.6 | Improved |
| add KGAT to SALC | SALC on Faster R-CNN · FLIR-ADAS | mAP50 (clean): 64.2 vs 62.3 clean (STD vs SALC+KGAT) | Hurt |
| adversarial training instead of standard training | STD on DINO · M3FD | mAP50 (clean): 86.9 -> 81.6 clean | Hurt |
Closest papers by meaning
- DEAL: Data-Efficient Adversarial Learning for High-Quality Infrared Imaging (CVPR 2025 · similarity 0.87)
- KDAT: Inherent Adversarial Robustness via Knowledge Distillation with Adversarial Tuning for Object Detection Models (AAAI 2025 · similarity 0.85)
- Rethinking Evaluation of Infrared Small Target Detection (NeurIPS 2025 · similarity 0.85)
- Semi-supervised Infrared Small Target Detection with Thermodynamic-Inspired Uneven Perturbation and Confidence Adaptation (AAAI 2025 · similarity 0.83)
- Rethinking Infrared Small Target Detection: A Foundation Driven Efficient Paradigm (NeurIPS 2026 · similarity 0.83)
- PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object Detection (AAAI 2025 · similarity 0.82)
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.
