Research map / Vision-language and multimodal / Human and embodied modeling
Text-IRSTD: Leveraging Semantic Text to Promote Infrared Small Target Detection in Complex Scenes
Feng Huang, Shuyuan Zheng, Zhaobing Qiu, Huanxian Liu, Huanxin Bai, Liqiong Chen
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 fuzzy semantic text prompt guidance to the IRSTD network (ablation) | Text-IRSTD · IRSTD-1k | IoU (%): 65.50 -> 69.57 | Improved |
| Add text guidance on NUDT-SIRST where visual features are already strong (ablation) | Text-IRSTD · NUDT-SIRST | IoU (%): 95.25 -> 95.84 | Improved |
| Use fuzzy scenario prompt instead of conventional class prompt (ablation) | Text-IRSTD · IRSTD-1k | IoU (%): 62.22 -> 69.57 | Improved |
| Add scene background description to the prompt (ablation) | Text-IRSTD · IRSTD-1k | IoU (%): 62.22 -> 66.65 | Improved |
| Add TGFA block to baseline (ablation) | Text-IRSTD · IRSTD-1k | IoU (%): 61.67 -> 67.75 | Improved |
| Add TGSI block to baseline (ablation) | Text-IRSTD · IRSTD-1k | IoU (%): 61.67 -> 66.19 | Improved |
| Combine TGFA and TGSI (ablation) | Text-IRSTD · IRSTD-1k | IoU (%): 67.75 -> 69.57 | Improved |
| Add detail perception module (DPM) in TGFA (ablation) | TGFA · IRSTD-1k | IoU (%): 67.16 -> 69.57 | Improved |
| Add channel attention (CA) in TGFA (ablation) | TGFA · IRSTD-1k | IoU (%): 68.01 -> 69.57 | Improved |
| Modulate image features with text-derived gain and offset instead of concatenation (ablation) | TGSI · IRSTD-1k | IoU (%): 67.73 -> 69.57 | Improved |
| Add gain parameter alpha_t in TGSI (ablation) | TGSI · IRSTD-1k | IoU (%): 66.65 -> 69.57 | Improved |
| Add offset parameter beta_t in TGSI (ablation) | TGSI · IRSTD-1k | Fa (1e-6): 16.22 -> 14.97 | No clear effect |
Closest papers by meaning
- SAIST: Segment Any Infrared Small Target Model Guided by Contrastive Language-Image Pretraining (CVPR 2025 · similarity 0.88)
- Rethinking Infrared Small Target Detection: A Foundation Driven Efficient Paradigm (NeurIPS 2026 · similarity 0.88)
- IRPruneDet: Efficient Infrared Small Target Detection via Wavelet Structure-Regularized Soft Channel Pruning (AAAI 2024 · similarity 0.87)
- Rethinking Evaluation of Infrared Small Target Detection (NeurIPS 2025 · similarity 0.87)
- Motion Prior Knowledge Learning with Homogeneous Language Descriptions for Moving Infrared Small Target Detection (AAAI 2025 · similarity 0.86)
- Semi-supervised Infrared Small Target Detection with Thermodynamic-Inspired Uneven Perturbation and Confidence Adaptation (AAAI 2025 · similarity 0.85)
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.
