Research map / Detection and segmentation / CNN features
IRSAM: Advancing Segment Anything Model for Infrared Small Target Detection
Mingjin Zhang, Yuchun Wang, Jie Guo, Yunsong Li, Xinbo Gao, Jing Zhang
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 WPMD blocks to the SAM encoder (ablation) | IRSAM · NUAA-SIRST | IoU (%): 78.73 -> 80.78 | Improved |
| add WPMD blocks to the SAM encoder (ablation) | IRSAM · NUAA-SIRST | Fa (1e-6): 11.18 -> 3.95 | Improved |
| add Granularity-Aware Decoder (GAD) (ablation) | IRSAM · NUAA-SIRST | IoU (%): 79.00 -> 80.78 | Improved |
| add GAD (ablation) | IRSAM · NUAA-SIRST | Fa (1e-6): 2.13 -> 3.95 | Hurt |
| add both WPMD and GAD to Mobile-SAM baseline (ablation) | Mobile-SAM · NUAA-SIRST | IoU (%): 75.84 -> 80.78 | Improved |
| increase number of WPMD blocks from 1 to 4 (ablation) | IRSAM · NUAA-SIRST | IoU (%): 76.17 -> 79.00 | Improved |
| feed both shallow and deep encoder features to GAD (ablation) | IRSAM · NUAA-SIRST | IoU (%): 78.64 -> 80.78 | Improved |
| WPMD instead of decoder fine-tuning or AdaptFormer on SAM ViT-B | SAM ViT-B · NUAA-SIRST | IoU (%): 67.90 -> 74.15 | Improved |
| scale SAM backbone from ViT-B to ViT-H with finetuned decoder | SAM · NUAA-SIRST | IoU (%): 67.45 -> 70.96 | Improved |
| IRSAM lightweight ViT-Tiny vs SAM ViT-H with WPMD | IRSAM · NUAA-SIRST | IoU (%): 75.96 -> 80.78 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ISNet — ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation (ICCV 2021) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Rethinking Evaluation of Infrared Small Target Detection (NeurIPS 2025 · similarity 0.88)
- SAIST: Segment Any Infrared Small Target Model Guided by Contrastive Language-Image Pretraining (CVPR 2025 · similarity 0.88)
- IRPruneDet: Efficient Infrared Small Target Detection via Wavelet Structure-Regularized Soft Channel Pruning (AAAI 2024 · similarity 0.87)
- 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 0.86)
- TCI-Former: Thermal Conduction-Inspired Transformer for Infrared Small Target Detection (AAAI 2024 · 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.
