# Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition

arXiv: https://arxiv.org/abs/2510.20284 · HTML: https://mlsanity.com/paper/2510.20284/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 78 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Builds on (most cited first, 29 of 29)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [TinyViT: Fast Pretraining Distillation for Small Vision Transformers](https://mlsanity.com/paper/2207.10666/) (2022)
- [EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention](https://mlsanity.com/paper/2305.07027/) (2023)
- [FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization](https://mlsanity.com/paper/2303.14189/) (2023)
- [CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention](https://mlsanity.com/paper/2108.00154/) (2021)
- [Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling](https://mlsanity.com/paper/1710.11431/) (2017)
- [EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications](https://mlsanity.com/paper/2206.10589/) (2022)
- [Rethinking Vision Transformers for MobileNet Size and Speed](https://mlsanity.com/paper/2212.08059/) (2022)
- [ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network](https://mlsanity.com/paper/1811.11431/) (2018)
- [ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction](https://mlsanity.com/paper/2105.10446/) (2021)
- [White-Box Transformers via Sparse Rate Reduction](https://mlsanity.com/paper/2306.01129/) (2023)
- [Label-Free Supervision of Neural Networks with Physics and Domain Knowledge](https://mlsanity.com/paper/1609.05566/) (2016)
- [Entropy and mutual information in models of deep neural networks](https://mlsanity.com/paper/1805.09785/) (2018)
- [Frequency-aware Feature Fusion for Dense Image Prediction](https://mlsanity.com/paper/2408.12879/) (2024)
- [YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection](https://mlsanity.com/paper/2308.05480/) (2023)
- [Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation](https://mlsanity.com/paper/2408.04804/) (2024)
- [InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding](https://mlsanity.com/paper/2306.04842/) (2023)
- [Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification](https://mlsanity.com/paper/2208.08741/) (2022)
- [GhostNetV3: Exploring the Training Strategies for Compact Models](https://mlsanity.com/paper/2404.11202/) (2024)
- [BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-task Dense Predictions](https://mlsanity.com/paper/2312.13514/) (2023)
- [Scaling White-Box Transformers for Vision](https://mlsanity.com/paper/2405.20299/) (2024)
- [Learning to Compress: Local Rank and Information Compression in Deep Neural Networks](https://mlsanity.com/paper/2410.07687/) (2024)
- [Physics Inspired Hybrid Attention for SAR Target Recognition](https://mlsanity.com/paper/2309.15697/) (2023)
- [CVGG-Net: Ship Recognition for SAR Images Based on Complex-Valued Convolutional Neural Network](https://mlsanity.com/paper/2305.07918/) (2023)

## Abstract (arXiv)

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.