Projection-Evidence Collaborative Optimization for Cross-Modal Few-Shot SAR Target Detection

Existing few-shot object detection (FSOD) methods face a dual challenge when applied to few-shot synthetic aperture radar target detection in cross-modal scenarios (optical$\rightarrow$SAR): (i) high-dimensional noisy features and nonlinear modality differences make traditional feature-alignment mechanisms ineffective for matching optical and SAR modalities; (ii) current probabilistic classification frameworks, which rely on point estimates under maximum likelihood estimation (MLE), cannot adequately model the epistemic uncertainty induced by sample scarcity, leading to over-confident detection errors. To address these issues, we propose a projection-evidence collaborative optimization (PECO) method for cross-modal few-shot SAR target detection. Specifically, we first design a projection distribution alignment (PDA) module, which constructs projected distributions and maps cross-modal data into a low-dimensional latent space, markedly reducing modality discrepancies and achieving effective cross-modal distribution alignment. Second, we introduce a dynamic uncertainty calibration (DUC) module that models class probabilities with a Dirichlet evidence distribution and jointly optimizes epistemic and aleatoric uncertainties through a dynamic-weighting and label-driven calibration mechanism, thereby mitigating over-confidence errors in scarce-sample settings. Experimental results on the cross-modal datasets DIOR2SSDD and FAIR1M2SAR-AIRcraft verify the effectiveness of the proposed approach: PECO surpasses existing state-of-the-art methods by 5.6% and 13.7%, respectively, in overall average detection performance, while also significantly improving model generalization. Code will be available at:https://github.com/Caltech-Z/PECO