# SPARK-SAM: Learning How to Prompt and Respond for Infrared Small Target Segmentation

arXiv: https://arxiv.org/abs/2608.20754 · HTML: https://mlsanity.com/paper/2608.20754/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 19 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Builds on (most cited first, 12 of 12)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Structured Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/1903.04197/) (2019)
- [EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything](https://mlsanity.com/paper/2312.00863/) (2023)
- [Asymmetric Contextual Modulation for Infrared Small Target Detection](https://mlsanity.com/paper/2009.14530/) (2020)
- [SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More](https://mlsanity.com/paper/2408.04579/) (2024)
- [EdgeSAM: Prompt-In-the-Loop Distillation for SAM](https://mlsanity.com/paper/2312.06660/) (2023)
- [RemoteSAM: Towards Segment Anything for Earth Observation](https://mlsanity.com/paper/2505.18022/) (2025)
- [RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation](https://mlsanity.com/paper/2508.04190/) (2025)
- [Seeing Through the Noise: Improving Infrared Small Target Detection and Segmentation from Noise Suppression Perspective](https://mlsanity.com/paper/2508.06878/) (2025)
- [One Shot is Enough for Sequential Infrared Small Target Segmentation](https://mlsanity.com/paper/2408.04823/) (2024)
- [SAM2-UNeXT: An Improved High-Resolution Baseline for Adapting Foundation Models to Downstream Segmentation Tasks](https://mlsanity.com/paper/2508.03566/) (2025)

## Abstract (arXiv)

Promptable segmentation models provide a reusable interface, but direct transfer to automatic infrared small-target segmentation (IRSTD) exposes a mismatch between spatial prompts and target-domain mask responses. In a diagnostic using target-covering loose-box prompts deterministically derived from test reference masks, the best official SAM2.1 results are only 4.69%, 1.64%, and 2.28% IoU on NUAA-SIRST, NUDT-SIRST, and IRSTD-1K. We introduce SPARK-SAM (Self-Prompt Adaptation with Response Knowledge for SAM), which learns target-domain response knowledge and conditions the decoder through an image-conditioned joint self-prompt state. Training combines benchmark-mask supervision with reliability-aware response guidance. SPARK-SAM achieves 75.78%, 86.49%, and 68.34% IoU with 0.726M additional parameters, ranking first on two benchmarks among 14 retrained SAM variants and adaptations evaluated as automatic image-to-mask methods. The staged IRSTD-1K diagnostic shows that response adaptation reaches most of the final IoU before the predicted points acquire reliable target grounding. Prompt supervision aligns the predicted prompt candidates with target locations, and frozen-weight interventions measure output sensitivity to the joint self-prompt state. Matched ablations show consistent accuracy gains from response guidance and high-resolution prompt refinement across all three datasets. Code is available at https://github.com/Sakauma/SPARK-SAM.