Search papers, labs, and topics across Lattice.
This paper reframes infrared small target detection (IRSTD) as a centroid regression task, arguing that precise target localization is more crucial than pixel-level segmentation given the targets' small size and blurred boundaries. They introduce SPIRE, a Single-Point Supervision guided Infrared Probabilistic Response Encoding method, which uses a Point-Response Prior Supervision (PRPS) to transform single-point annotations into probabilistic response maps. Experiments on IRSTD benchmarks demonstrate that SPIRE achieves competitive detection performance with low false alarm rates and reduced computational cost compared to segmentation-based methods.
Rethinking IRSTD as a centroid regression problem with single-point supervision achieves competitive detection performance with significantly reduced computational cost, challenging the dominance of pixel-level segmentation approaches.
Infrared small target detection (IRSTD) aims to separate small targets from clutter backgrounds. Extensive research is dedicated to the pixel-level supervision-guided"encoder-decoder"segmentation paradigm. Although having achieved promising performance, they neglect the fact that small targets only occupy a few pixels and are usually accompanied with blurred boundary caused by clutter backgrounds. Based on this observation, we argue that the first principle of IRSTD should be target localization instead of separating all target region accompanied with indistinguishable background noise. In this paper, we reformulate IRSTD as a centroid regression task and propose a novel Single-Point Supervision guided Infrared Probabilistic Response Encoding method (namely, SPIRE), which is indeed challenging due to the mismatch between reduced supervision network and equivalent output. Specifically, we first design a Point-Response Prior Supervision (PRPS), which transforms single-point annotations into probabilistic response map consistent with infrared point-target response characteristics, with a High-Resolution Probabilistic Encoder (HRPE) that enables encoder-only, end-to-end regression without decoder reconstruction. By preserving high-resolution features and increasing effective supervision density, SPIRE alleviates optimization instability under sparse target distributions. Finally, extensive experiments on various IRSTD benchmarks, including SIRST-UAVB and SIRST4 demonstrate that SPIRE achieves competitive target-level detection performance with consistently low false alarm rate (Fa) and significantly reduced computational cost. Code is publicly available at: https://github.com/NIRIXIANG/SPIRE-IRSTD.
Tsinghua AI