One Shot is Enough for Sequential Infrared Small Target Segmentation
This work addresses the problem of segmenting small targets in infrared sequences for applications like surveillance or remote sensing, offering a data-efficient solution but is incremental as it builds on SAM.
The paper tackles sequential infrared small target segmentation by proposing a one-shot, training-free method that adapts the Segment Anything Model (SAM) to this domain, achieving comparable performance to state-of-the-art methods with only one reference image.
Infrared small target sequences exhibit strong similarities between frames and contain rich contextual information, which motivates us to achieve sequential infrared small target segmentation (IRSTS) with minimal data. Inspired by the success of Segment Anything Model (SAM) across various downstream tasks, we propose a one-shot and training-free method that perfectly adapts SAM's zero-shot generalization capability to sequential IRSTS. Specifically, we first obtain a confidence map through local feature matching (LFM). The highest point in the confidence map is used as the prompt to replace the manual prompt. Then, to address the over-segmentation issue caused by the domain gap, we design the point prompt-centric focusing (PPCF) module. Subsequently, to prevent miss and false detections, we introduce the triple-level ensemble (TLE) module to produce the final mask. Experiments demonstrate that our method requires only one shot to achieve comparable performance to state-of-the-art IRSTS methods and significantly outperforms other one-shot segmentation methods. Moreover, ablation studies confirm the robustness of our method in the type of annotations and the selection of reference images.