Research map / Detection and segmentation / CNN features
Rethinking IRSTD: Single-Point Supervision Guided Encoder-only Framework is Enough for Infrared Small Target Detection
Rixiang Ni, Boyang Li, Chen Jun, Zhijie Chen, Feiyu Ren, Yuji Wang, Haoyang Yuan, Wujiao He, Wei An
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 |
|---|---|---|---|
| use PRPS response maps instead of single-point impulse supervision (ablation) | SPIRE · SIRST-UAVB (2400:600 split) | F1: 94.27 -> 97.05 | Improved |
| add contrast-aware modulation (PRPS) over unconstrained Gaussian supervision (ablation) | SPIRE · SIRST-UAVB (2400:600 split) | Fa (1e-8): 2.44 -> 1.02 | Improved |
| use sigma=2 instead of sigma=1 in PRPS (ablation) | SPIRE · SIRST-UAVB (2400:600 split) | Fa (1e-8): 5.26 -> 1.02 | Improved |
| use sigma=2 instead of sigma=3 in PRPS (ablation) | SPIRE · SIRST-UAVB (2400:600 split) | recall (Pd): 92.50 -> 94.44 | Improved |
| use output stride 4 instead of 8 (ablation) | SPIRE · SIRST-UAVB (2400:600 split) | recall (Pd): 83.98 -> 94.44 | Improved |
| use output stride 4 instead of 2 (ablation) | SPIRE · SIRST-UAVB (2400:600 split) | FLOPs (G): 26.77 -> 7.68 | Improved |
| use output stride 2 instead of 4 (lower Fa, lower F1) (ablation) | SPIRE · SIRST-UAVB (2400:600 split) | Fa (1e-8): 1.02 -> 0.81 | Mixed |
| add channel reorganization units (ablation) | SPIRE · SIRST-UAVB (2400:600 split) | Fa (1e-8): 5.33 -> 1.02 | Improved |
| add channel reweighting (ablation) | SPIRE · SIRST-UAVB (2400:600 split) | Fa (1e-8): 8.15 -> 1.02 | Improved |
| use matching threshold delta=3 instead of 5 (ablation) | SPIRE · SIRST4 (2285:1067 split) | F1: 94.74 vs. 94.60 | No clear effect |
Closest papers by meaning
- Rethinking Evaluation of Infrared Small Target Detection (NeurIPS 2025 · similarity 0.91)
- SAIST: Segment Any Infrared Small Target Model Guided by Contrastive Language-Image Pretraining (CVPR 2025 · similarity 0.89)
- IRPruneDet: Efficient Infrared Small Target Detection via Wavelet Structure-Regularized Soft Channel Pruning (AAAI 2024 · similarity 0.88)
- Semi-supervised Infrared Small Target Detection with Thermodynamic-Inspired Uneven Perturbation and Confidence Adaptation (AAAI 2025 · similarity 0.88)
- Infrared Small Target Detection with Scale and Location Sensitivity (CVPR 2024 · similarity 0.88)
- Rethinking Infrared Small Target Detection: A Foundation Driven Efficient Paradigm (NeurIPS 2026 · similarity 0.88)
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.
