Revisiting the Scale Loss Function and Gaussian-Shape Convolution for Infrared Small Target Detection
For researchers in infrared small target detection, this work provides a principled loss function and convolution kernel that improve detection performance and training stability.
The paper addresses training instability and inadequate spatial attention in infrared small target detection by proposing a diff-based scale loss with monotonic gradients and Gaussian-shaped convolution with rotated pinwheel masks, achieving consistent improvements in mIoU, Pd, and Fa over SOTA on three benchmarks.
Infrared small target detection still faces two persistent challenges: training instability from non-monotonic scale loss functions, and inadequate spatial attention due to generic convolution kernels that ignore the physical imaging characteristics of small targets. In this paper, we revisit both aspects. For the loss side, we propose a \emph{diff-based scale loss} that weights predictions according to the signed area difference between the predicted mask and the ground truth, yielding strictly monotonic gradients and stable convergence. We further analyze a family of four scale loss variants to understand how their geometric properties affect detection behavior. For the spatial side, we introduce \emph{Gaussian-shaped convolution} with a learnable scale parameter to match the center-concentrated intensity profile of infrared small targets, and augment it with a \emph{rotated pinwheel mask} that adaptively aligns the kernel with target orientation via a straight-through estimator. Extensive experiments on IRSTD-1k, NUDT-SIRST, and SIRST-UAVB demonstrate consistent improvements in $mIoU$, $P_d$, and $F_a$ over state-of-the-art methods. We release our anonymous code and pretrained models.