Temporal-Emerged Prompting for Segment Anything in Multiframe Infrared Small Target Detection

Yinghui Xing, Donghao Chu, Shizhou Zhang, Di Xu
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:140031-140045, 2026.

Abstract

Accurately localizing and segmenting small targets in low signal-to-noise ratio (SNR) infrared sequences remains a challenging task. Since targets are often indistinguishable from the background in individual frames, existing methods, even when equipped with advanced foundation model and powerful inter-frame association mechanisms, still fail to detect them. Motivated by the observation that targets tend to emerge gradually from the background over time and become distinguishable, we propose Temporal-Emerged Prompting for Segment Anything Model (TEP-SAM), a principled framework designed to explicitly exploit such temporal-emerged cues to modulate and prompt SAM. TEP-SAM operates by jointly modeling global motion patterns and local motion deviations to locate potential targets. It further enhances target region features by leveraging motion discrepancy, thereby generating temporal-emerged cues for SAM and enabling non-interactive segmentation. By bridging large-scale semantic pretraining with task-specific temporal modeling, TEP-SAM effectively adapts SAM to the challenging multiframe infrared small target detection task. Extensive experiments demonstrate the effectiveness of our approach, particularly under severely low-SNR conditions and in complex dynamic background.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-xing26b, title = {Temporal-Emerged Prompting for Segment Anything in Multiframe Infrared Small Target Detection}, author = {Xing, Yinghui and Chu, Donghao and Zhang, Shizhou and Xu, Di}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {140031--140045}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/xing26b/xing26b.pdf}, url = {https://proceedings.mlr.press/v306/xing26b.html}, abstract = {Accurately localizing and segmenting small targets in low signal-to-noise ratio (SNR) infrared sequences remains a challenging task. Since targets are often indistinguishable from the background in individual frames, existing methods, even when equipped with advanced foundation model and powerful inter-frame association mechanisms, still fail to detect them. Motivated by the observation that targets tend to emerge gradually from the background over time and become distinguishable, we propose Temporal-Emerged Prompting for Segment Anything Model (TEP-SAM), a principled framework designed to explicitly exploit such temporal-emerged cues to modulate and prompt SAM. TEP-SAM operates by jointly modeling global motion patterns and local motion deviations to locate potential targets. It further enhances target region features by leveraging motion discrepancy, thereby generating temporal-emerged cues for SAM and enabling non-interactive segmentation. By bridging large-scale semantic pretraining with task-specific temporal modeling, TEP-SAM effectively adapts SAM to the challenging multiframe infrared small target detection task. Extensive experiments demonstrate the effectiveness of our approach, particularly under severely low-SNR conditions and in complex dynamic background.} }
Endnote
%0 Conference Paper %T Temporal-Emerged Prompting for Segment Anything in Multiframe Infrared Small Target Detection %A Yinghui Xing %A Donghao Chu %A Shizhou Zhang %A Di Xu %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-xing26b %I PMLR %P 140031--140045 %U https://proceedings.mlr.press/v306/xing26b.html %V 306 %X Accurately localizing and segmenting small targets in low signal-to-noise ratio (SNR) infrared sequences remains a challenging task. Since targets are often indistinguishable from the background in individual frames, existing methods, even when equipped with advanced foundation model and powerful inter-frame association mechanisms, still fail to detect them. Motivated by the observation that targets tend to emerge gradually from the background over time and become distinguishable, we propose Temporal-Emerged Prompting for Segment Anything Model (TEP-SAM), a principled framework designed to explicitly exploit such temporal-emerged cues to modulate and prompt SAM. TEP-SAM operates by jointly modeling global motion patterns and local motion deviations to locate potential targets. It further enhances target region features by leveraging motion discrepancy, thereby generating temporal-emerged cues for SAM and enabling non-interactive segmentation. By bridging large-scale semantic pretraining with task-specific temporal modeling, TEP-SAM effectively adapts SAM to the challenging multiframe infrared small target detection task. Extensive experiments demonstrate the effectiveness of our approach, particularly under severely low-SNR conditions and in complex dynamic background.
APA
Xing, Y., Chu, D., Zhang, S. & Xu, D.. (2026). Temporal-Emerged Prompting for Segment Anything in Multiframe Infrared Small Target Detection. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:140031-140045 Available from https://proceedings.mlr.press/v306/xing26b.html.

Related Material