Research map / Video / Video segmentation and tracking
CHAL: Causal-guided Hierarchical Anomaly-aware Learning for Moving Infrared Small Target Detection
Weiwei Duan, Luping Ji, Shipeng Lei, Sicheng Zhu, Jianghong Huang, Mao Ye
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 spatio-temporal neural fields (SNF) (ablation) | CHAL · DAUB-H | mAP50 (%): 23.48 -> 43.76 | Improved |
| add hierarchical anomaly-aware learning (HAL) on top of SNF (ablation) | CHAL · DAUB-H | mAP50 (%): 43.76 -> 48.63 | Improved |
| add causal relation guiding (CRG) on top of SNF and HAL (ablation) | CHAL · DAUB-H | mAP50 (%): 48.63 -> 54.28 | Improved |
| add causal relation guiding (CRG) on top of SNF and HAL (ablation) | CHAL · NUDT-MIRSDT | F1 (%): 82.73 -> 87.41 | Improved |
| replace self-attention with CRG (ablation) | CHAL · DAUB-H | mAP50 (%): 49.85 -> 54.28 | Improved |
| replace CBAM with CRG (ablation) | CHAL · NUDT-MIRSDT | mAP50 (%): 70.18 -> 75.25 | Improved |
| add causal feature refining (C3) to CRG (ablation) | CHAL · DAUB-H | mAP50 (%): 53.19 -> 54.28 | Improved |
| add causal-guided gating (C2) without C3 versus C3 without C2 (ablation) | CHAL · NUDT-MIRSDT | mAP50 (%): 72.73 -> 73.82 | Improved |
| use only appearance anomaly without HAL on weak anomalies (ablation) | CHAL variants · synthetic NUDT-MIRSDT, strength below 0.4 | F1 | Hurt |
| use CHAL instead of anomaly-detection method DiffusionAD for infrared targets | CHAL · DAUB-H | mAP50 (%): 19.50 -> 54.28 | Improved |
| apply CHAL to visible-light remote sensing | CHAL · RsCarData | mAP50 (%): 52.41 -> 57.37 | Improved |
| CHAL versus ADSUNet on precision | CHAL · NUDT-MIRSDT | Precision (%): 92.50 -> 86.35 | Hurt |
Closest papers by meaning
- Rethinking Infrared Small Target Detection: A Foundation Driven Efficient Paradigm (NeurIPS 2026 · similarity 0.86)
- Semi-supervised Infrared Small Target Detection with Thermodynamic-Inspired Uneven Perturbation and Confidence Adaptation (AAAI 2025 · similarity 0.85)
- Rethinking Evaluation of Infrared Small Target Detection (NeurIPS 2025 · similarity 0.85)
- Motion Prior Knowledge Learning with Homogeneous Language Descriptions for Moving Infrared Small Target Detection (AAAI 2025 · similarity 0.85)
- IRPruneDet: Efficient Infrared Small Target Detection via Wavelet Structure-Regularized Soft Channel Pruning (AAAI 2024 · similarity 0.84)
- Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target 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.
