{"ID":2851033,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.20284","arxiv_id":"2510.20284","title":"Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition","abstract":"Deep learning models for complex-valued Synthetic Aperture Radar (CV-SAR) image recognition are fundamentally constrained by a representation trilemma under data-limited and domain-shift scenarios: the concurrent, yet conflicting, optimization of generalization, interpretability, and efficiency. Our work is motivated by the premise that the rich electromagnetic scattering features inherent in CV-SAR data hold the key to resolving this trilemma, yet they are insufficiently harnessed by conventional data-driven models. To this end, we introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel \"compression-aggregation-compression\" architecture. The first stage performs a physics-guided compression, wherein a novel dictionary processor adaptively embeds physical priors, enabling a compact unfolding network to efficiently extract sparse, physically-grounded signatures. A subsequent aggregation module enriches these representations, followed by a final semantic compression stage that utilizes a compact classification head with self-distillation to learn maximally task-relevant and discriminative embeddings. We instantiate KINN in both CNN (0.7M) and Vision Transformer (0.95M) variants. Extensive evaluations on five SAR benchmarks confirm that KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios and tangible interpretability, thereby providing an effective solution to the representation trilemma and offering a new path for trustworthy AI in SAR image analysis.","short_abstract":"Deep learning models for complex-valued Synthetic Aperture Radar (CV-SAR) image recognition are fundamentally constrained by a representation trilemma under data-limited and domain-shift scenarios: the concurrent, yet conflicting, optimization of generalization, interpretability, and efficiency. Our work is motivated b...","url_abs":"https://arxiv.org/abs/2510.20284","url_pdf":"https://arxiv.org/pdf/2510.20284v1","authors":"[\"Haodong Yang\",\"Zhongling Huang\",\"Shaojie Guo\",\"Zhe Zhang\",\"Gong Cheng\",\"Junwei Han\"]","published":"2025-10-23T07:12:26Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Vision Transformer\",\"Transformer\",\"Convolutional Neural Network\"]","has_code":false}