High Resolution Range Profile (HRRP), with its concise vector representation and rich structural information, has become the primary focus of research in the field of Radar Automatic Target Recognition (RATR) in Sensors community. In actual combat situations, due to limitations in sensing conditions, acquiring data from non-cooperative targets is challenging. Consequently, identifying HRRP targets in the absence of sufficient data is a significant and urgent issue that requires immediate attention. Additionally, precise target recognition represents a pressing hurdle. To this end, this paper proposes a maksed Vision Transformer (ViT) and brownian distance covariance classifier (MTBC). The ViT is initially pre-trained through a self-supervised learning strategy of masked reconstruction, which enables the model to gain a comprehensive understanding of the intricate interconnections between neighbouring blocks in HRRP, thereby facilitating the extraction of more nuanced and discriminative features. Additionally, within the context of prototype learning in few-shot metric learning, a brownian distance covariance metric-based classifier is devised. This combines a parametric feature extractor and a non-parametric metric classifier, enabling the accurate description of the dependency between support class prototypes and query vectors. Experimental results validated on measured HRRP dataset demonstrate that the proposed method performs superiorly in few-shot HRRP target recognition task.

In real-world scenarios, radar systems need to recognize both known and unknown classes, referred to as open set recognition (OSR). Prototype-like methods have shown significant potential in addressing this challenging task. However, prototype learning overlooks the directional relationship between feature embeddings and prototypes, leading to open space risk. In addition, strong learning for known classes can weaken the sensitivity to sample variations, impacting OSR performance of the model. To address these issues, we propose the regularization-based region learning (RBRL) method. Firstly, from the perspective of gradient propagation, RBRL demonstrates that l₂-regularization can enhance the sensitivity of logit vector directions to sample variations. Unlike in closed-set scenarios, l₂-regularization can effectively improve OSR performance even with sufficient training data. Secondly, RBRL minimizes the known space in both distance and angular domains by leveraging the spatial geometric relationship between prototypes and feature embeddings, mitigating open space risk. Furthermore, decision-level fusion is achieved by computing the area of the fan-shaped region in RBRL. The effectiveness of RBRL is validated on datasets comprising both measured and simulated high resolution range profiles (HRRPs). RBRL achieves state-of-the-art performance across various OSR metrics.

In recent years, radar automatic target recognition (RATR) utilizing high-resolution range profiles (HRRPs) has received significant attention. Approaches based on deep learning have demonstrated remarkable efficacy in HRRP recognition tasks. However, the performance of neural networks is notably vulnerable to noise, leading to a detrimental effect on their recognition accuracy and overall robustness. To address this issue, a residual scattering attention network (RSAN) is proposed for HRRP target recognition, which comprises a residual scattering network, ResNet18, and a self-attention module. The residual scattering network is designed to suppress noise components and extract noise-robust features. It is derived from the improvement of a scattering network and does not need to learn parameters from the data. ResNet18 is employed for the purpose of extracting a deep representation of scattering features for HRRPs. Furthermore, a self-attention module is integrated into ResNet18, enabling the model to focus on target regions, thereby enhancing its feature-learning capability. The effectiveness and noise robustness of the proposed method are validated through experiments conducted on two measured datasets.

The actual application of Radar Automatic Target Recognition (RATR) based on High Resolution Range Profile (HRRP) in open set environment is of significant practical importance. Implementing RATR in open set environment requires the system to correctly classify known classes of targets while ensuring known and unknown classes are distinguishable in the feature space. Additionally, the score function must be constructed for the system's decision module to reject unknown classes. To address these challenges, we propose a Expansive Consistency-Aware Prototype Learning (ECAPL) framework for Open Set Recognition (OSR). First, we propose Expansive Guidance Point Learning (EGPL), which strategically employs guidance prototype points with elastic binding constraints to enforce separation between known and unknown classes. By combining guidance points with an ideal prototype margin constraint, EGPL produces a compact abating score function for the decision module. Second, a Twin-Entanglement Framework (TEF) is proposed to leverage inconsistent unknown-class feature distributions across multiple experiments. Through dual-space correlation analysis, TEF enhances the discriminative power of prototype representations. Experimental results on measured HRRP datasets demonstrate the effectiveness and robustness of the proposed approach.

High-Resolution Range Profile (HRRP) represents the electromagnetic backscattering distribution of targets and plays a pivotal role in remote-sensing-based Automatic Target Recognition (RATR). However, in non-cooperative sensing scenarios, acquiring sufficient measured data is severely constrained by operational costs and physical limitations, leading to data scarcity that hampers model robustness. To overcome this, we propose SpecM-DDPM, a spectral-aware Denoising Diffusion Probabilistic Models (DDPM) tailored for generating high-fidelity HRRPs that preserve physical scattering properties. Unlike generic generative models, SpecM-DDPM incorporates radar signal physics into the diffusion process. Specifically, a parallel multi-scale block is designed to adaptively capture both local scattering centers and global target resonance structures. To ensure spectral fidelity, a spectral gating mechanism serves as a physics-constrained filter to calibrate the energy distribution in the frequency domain. Furthermore, a Frequency-Aware Curriculum Learning (FACL) strategy is introduced to guide the progressive reconstruction from low-frequency structural components to high-frequency scattering details. Experiments on measured aircraft data demonstrate that SpecM-DDPM generates samples with high physical consistency, significantly enhancing the generalization performance of radar recognition systems in data-limited environments.

Deep neural networks have been widely used in the field of high-resolution range profile (HRRP) radar automatic target recognition (RATR) and have achieved promising results. However, when a new target class appears, how the deep neural networks learns new knowledge and updates the model is still an emerging problem. Directly using the new target class samples to train the deep neural networks will cause the problem of “catastrophic forgetting”. In this paper, we propose a two-stage distillation learning method, PFDE-DCN, to solve the HRRP class incremental learning (CIL) problem. Firstly, we use a machine learning boosting algorithm to dynamically extend the network and a pooled distillation learning algorithm to enable knowledge migration between the old and new feature extraction networks. Then, we use the distillation learning method to compress the extended network. The distillation strategy keeps the critical network parameters and removes the redundant network parameters to avoid the infinite increase of model complexity. We conduct experiments on both simulated and measured aircraft HRRP datasets, and the experimental results show that our method PFDE-DCN obtains state-of-the-art performance.