Search

Food security is a critical issue closely linked to human being. With the increasing demand for food, international trade has become the main access to supplementing domestic food shortages, which not only alleviates local food shocks, but also exposes economies to global food crises. In this paper, we construct four temporal international crop trade networks (iCTNs) based on trade values of maize, rice, soybean and wheat, and describe the structural evolution of different iCTNs from{ {1993}} to 2018. We find that the size of all the four iCTNs expanded from{ {1993}} to 2018 with more participants and larger trade values. Our results show that the iCTNs not only become tighter according to the increasing in network density and clustering coefficient, but also get more similar. We also find that the iCTNs are not always disassortative, unlike the world cereal trade networks and other international commodity trade networks. The degree assortative coefficients depend on degree directions and crop types. The analysis about assortativity also indicates that economies with high out-degrees tend to connect with economies with low in-degrees and low out-degrees. Additionally, we compare the structure of the four iCTNs to enhance our understanding of the international food trade system. Although the overall evolutionary patterns of different iCTNs are similar, some crops exhibit idiosyncratic trade patterns. It highlights the need to consider different crop networks' idiosyncratic features while making food policies. Our findings about the dynamics of the iCTNs play an important role in understanding vulnerabilities in the global food system.

Despite large language models (LLMs) have demonstrated impressive performance in various tasks, they are still suffering from the factual inconsistency problem called hallucinations. For instance, LLMs occasionally generate content that diverges from source article, and prefer to extract information that appears at the beginning and end of the context, especially in long document summarization. Inspired by these findings, we propose to improve the faithfulness of LLMs in summarization by impelling them to process the entire article more fairly and faithfully. We present a novel summary generation strategy, namely SliSum, which exploits the ideas of sliding windows and self-consistency. Specifically, SliSum divides the source article into overlapping windows, and utilizes LLM to generate local summaries for the content in the windows. Finally, SliSum aggregates all local summaries using clustering and majority voting algorithm to produce more faithful summary of entire article. Extensive experiments demonstrate that SliSum significantly improves the faithfulness of diverse LLMs including LLaMA-2, Claude-2 and GPT-3.5 in both short and long text summarization, while maintaining their fluency and informativeness and without additional fine-tuning and resources. We further conduct qualitative and quantitative studies to investigate why SliSum works and impacts of hyperparameters in SliSum on performance., Comment: Long paper accepted at LREC-COLING 2024 (oral)

Neural networks (NNs) have demonstrated strong capabilities of representing high-dimensional, complex functional relations, and hence have been widely used to characterize complex constitutive relations for various types of materials, such as polycrystals, polymers, etc. However, to construct a reliable NN-based constitutive model, a considerable amount of data, i.e. stress-strain states along different loading paths is needed, which can be expensive to collect. To address such challenge, we develop a hybrid finite element method (FEM) - NN optimization framework to learn complex hyperelastic constitutive relations from full-field data. The key advantage of this framework is that it can make use of the non-uniform displacement field due to the geometric inhomogeneities for training NN-based constitutive models. Since such data can provide many different stress-strain states in a single test, it can greatly reduce the number of experiments needed for the training of NNs. Besides, we adopt a mechanics-informed neural network (MINN) as our architecture to ensure that our NN-based models satisfy all necessary physical constraints by construction, such as objectivity, material symmetry, polyconvexity, etc. Such architecture is also key to the convergence of our optimization framework. We then use both synthetic and experimental data to test the performance of our proposed framework on various isotropic hyperelastic materials. Results show that our optimization framework can be used to train NN-based constitutive models for hyperelastic materials with high accuracy and efficiency using data generated from simple tests, which can also be easily adapted to characterize complex constitutive models for a broader range of materials., Comment: 14 pages,7 figures

Recent advancements in Large Multimodal Models (LMMs) have leveraged extensive multimodal datasets to enhance capabilities in complex knowledge-driven tasks. However, persistent challenges in perceptual and reasoning errors limit their efficacy, particularly in interpreting intricate visual data and deducing multimodal relationships. Addressing these issues, we introduce a novel dataset format, PIN (Paired and INterleaved multimodal documents), designed to significantly improve both the depth and breadth of multimodal training. The PIN format is built on three foundational principles: knowledge intensity, scalability, and support for diverse training modalities. This innovative format combines markdown files and comprehensive images to enrich training data with a dense knowledge structure and versatile training strategies. We present PIN-14M, an open-source dataset comprising 14 million samples derived from a diverse range of Chinese and English sources, tailored to include complex web and scientific content. This dataset is constructed meticulously to ensure data quality and ethical integrity, aiming to facilitate advanced training strategies and improve model robustness against common multimodal training pitfalls. Our initial results, forming the basis of this technical report, suggest significant potential for the PIN format in refining LMM performance, with plans for future expansions and detailed evaluations of its impact on model capabilities.

Artificial intelligence (AI) technology has demonstrated remarkable potential in drug dis-covery, where pharmacokinetics plays a crucial role in determining the dosage, safety, and efficacy of new drugs. A major challenge for AI-driven drug discovery (AIDD) is the scarcity of high-quality data, which often requires extensive wet-lab work. A typical example of this is pharmacokinetic experiments. In this work, we develop a physical formula enhanced mul-ti-task learning (PEMAL) method that predicts four key parameters of pharmacokinetics simultaneously. By incorporating physical formulas into the multi-task framework, PEMAL facilitates effective knowledge sharing and target alignment among the pharmacokinetic parameters, thereby enhancing the accuracy of prediction. Our experiments reveal that PEMAL significantly lowers the data demand, compared to typical Graph Neural Networks. Moreover, we demonstrate that PEMAL enhances the robustness to noise, an advantage that conventional Neural Networks do not possess. Another advantage of PEMAL is its high flexibility, which can be potentially applied to other multi-task machine learning scenarios. Overall, our work illustrates the benefits and potential of using PEMAL in AIDD and other scenarios with data scarcity and noise.

Visual detection of Micro Air Vehicles (MAVs) has attracted increasing attention in recent years due to its important application in various tasks. The existing methods for MAV detection assume that the training set and testing set have the same distribution. As a result, when deployed in new domains, the detectors would have a significant performance degradation due to domain discrepancy. In this paper, we study the problem of cross-domain MAV detection. The contributions of this paper are threefold. 1) We propose a Multi-MAV-Multi-Domain (M3D) dataset consisting of both simulation and realistic images. Compared to other existing datasets, the proposed one is more comprehensive in the sense that it covers rich scenes, diverse MAV types, and various viewing angles. A new benchmark for cross-domain MAV detection is proposed based on the proposed dataset. 2) We propose a Noise Suppression Network (NSN) based on the framework of pseudo-labeling and a large-to-small training procedure. To reduce the challenging pseudo-label noises, two novel modules are designed in this network. The first is a prior-based curriculum learning module for allocating adaptive thresholds for pseudo labels with different difficulties. The second is a masked copy-paste augmentation module for pasting truly-labeled MAVs on unlabeled target images and thus decreasing pseudo-label noises. 3) Extensive experimental results verify the superior performance of the proposed method compared to the state-of-the-art ones. In particular, it achieves mAP of 46.9%(+5.8%), 50.5%(+3.7%), and 61.5%(+11.3%) on the tasks of simulation-to-real adaptation, cross-scene adaptation, and cross-camera adaptation, respectively., Comment: 17 pages, 11 figures. Accepted by IEEE Transactions on Automation Science and Engineering

The Russia-Ukraine conflict is a growing concern worldwide and poses serious threats to regional and global food security. Using monthly trade data for maize, rice, and wheat from 2016/1 to 2022/12, this paper constructs three international crop trade networks (iCTNs) and an aggregate international food trade network (iFTN). We aim to examine the structural changes following the occurrence of the Russia-Ukraine conflict. We find significant shifts in the number of edges, average degree, density, efficiency, and natural connectivity in the third quarter of 2022, particularly in the international wheat trade network. Additionally, we have shown that political reasons have caused more pronounced changes in the trade connections between the economies of the North Atlantic Treaty Organization and Russia than with Ukraine. This paper could provide insights into the negative impact of geopolitical conflicts on the global food system and encourage a series of effective strategies to mitigate the negative impact of the conflict on global food trade.

In recent years, the recommendation content on e-commerce platforms has become increasingly rich -- a single user feed may contain multiple entities, such as selling products, short videos, and content posts. To deal with the multi-entity recommendation problem, an intuitive solution is to adopt the shared-network-based architecture for joint training. The idea is to transfer the extracted knowledge from one type of entity (source entity) to another (target entity). However, different from the conventional same-entity cross-domain recommendation, multi-entity knowledge transfer encounters several important issues: (1) data distributions of the source entity and target entity are naturally different, making the shared-network-based joint training susceptible to the negative transfer issue, (2) more importantly, the corresponding feature schema of each entity is not exactly aligned (e.g., price is an essential feature for selling product while missing for content posts), making the existing methods no longer appropriate. Recent researchers have also experimented with the pre-training and fine-tuning paradigm. Again, they only consider the scenarios with the same entity type and feature systems, which is inappropriate in our case. To this end, we design a pre-training & fine-tuning based Multi-entity Knowledge Transfer framework called MKT. MKT utilizes a multi-entity pre-training module to extract transferable knowledge across different entities. In particular, a feature alignment module is first applied to scale and align different feature schemas. Afterward, a couple of knowledge extractors are employed to extract the common and entity-specific knowledge. In the end, the extracted common knowledge is adopted for target entity model training. Through extensive offline and online experiments, we demonstrated the superiority of MKT over multiple State-Of-The-Art methods.

Network speeds grow quickly in the modern cloud, so SmartNICs are introduced to offload network processing tasks, even application logic. However, typical multicore SmartNICs such as BlueFiled-2 are only capable of processing control-plane tasks with their embedded processors that have limited memory bandwidth and computing power. On the other hand, cloud applications evolve rapidly, such that a limited number of fixed hardware engines in a SmartNIC cannot satisfy the requirements of cloud applications. Therefore, SmartNIC programmers call for a programmable datapath accelerator (DPA) to process network traffic at line rate. However, no existing work has unveiled the performance characteristics of the existing DPA. To this end, we present the first architectural characterization of the latest DPA-enhanced BlueFiled-3 (BF3) SmartNIC. Our evaluation results indicate that BF3's DPA is significantly wimpier than the off-path Arm processor and the host CPU. However, we still identify that DPA has three unique architectural characteristics that unleash the performance potential of DPA. Specifically, we demonstrate how to take advantage of DPA's three architectural characteristics regarding computing, networking, and memory subsystems. Then we propose three important guidelines for programmers to fully unleash the potential of DPA. To demonstrate the effectiveness of our approach, we conduct detailed case studies regarding each guideline. Our case study on key-value aggregation achieves up to 4.3$\times$ higher throughput by using our guidelines to optimize memory combinations., Comment: accepted by ICNP24

Vision-based estimation of the motion of a moving target is usually formulated as a bearing-only estimation problem where the visual measurement is modeled as a bearing vector. Although the bearing-only approach has been studied for decades, a fundamental limitation of this approach is that it requires extra lateral motion of the observer to enhance the target's observability. Unfortunately, the extra lateral motion conflicts with the desired motion of the observer in many tasks. It is well-known that, once a target has been detected in an image, a bounding box that surrounds the target can be obtained. Surprisingly, this common visual measurement especially its size information has not been well explored up to now. In this paper, we propose a new bearing-angle approach to estimate the motion of a target by modeling its image bounding box as bearing-angle measurements. Both theoretical analysis and experimental results show that this approach can significantly enhance the observability without relying on additional lateral motion of the observer. The benefit of the bearing-angle approach comes with no additional cost because a bounding box is a standard output of object detection algorithms. The approach simply exploits the information that has not been fully exploited in the past. No additional sensing devices or special detection algorithms are required.

In this technical report, we present TeleChat, a collection of large language models (LLMs) with parameters of 3 billion, 7 billion and 12 billion. It includes pretrained language models as well as fine-tuned chat models that is aligned with human preferences. TeleChat is initially pretrained on an extensive corpus containing a diverse collection of texts from both English and Chinese languages, including trillions of tokens. Subsequently, the model undergoes fine-tuning to align with human preferences, following a detailed methodology that we describe. We evaluate the performance of TeleChat on various tasks, including language understanding, mathematics, reasoning, code generation, and knowledge-based question answering. Our findings indicate that TeleChat achieves comparable performance to other open-source models of similar size across a wide range of public benchmarks. To support future research and applications utilizing LLMs, we release the fine-tuned model checkpoints of TeleChat's 7B and 12B variant, along with code and a portion of our pretraining data, to the public community., Comment: 28 pages, 2 figures

Visual detection of micro aerial vehicles (MAVs) has received increasing research attention in recent years due to its importance in many applications. However, the existing approaches based on either appearance or motion features of MAVs still face challenges when the background is complex, the MAV target is small, or the computation resource is limited. In this paper, we propose a global-local MAV detector that can fuse both motion and appearance features for MAV detection under challenging conditions. This detector first searches MAV target using a global detector and then switches to a local detector which works in an adaptive search region to enhance accuracy and efficiency. Additionally, a detector switcher is applied to coordinate the global and local detectors. A new dataset is created to train and verify the effectiveness of the proposed detector. This dataset contains more challenging scenarios that can occur in practice. Extensive experiments on three challenging datasets show that the proposed detector outperforms the state-of-the-art ones in terms of detection accuracy and computational efficiency. In particular, this detector can run with near real-time frame rate on NVIDIA Jetson NX Xavier, which demonstrates the usefulness of our approach for real-world applications. The dataset is available at https://github.com/WestlakeIntelligentRobotics/GLAD. In addition, A video summarizing this work is available at https://youtu.be/Tv473mAzHbU., Comment: 12 pages, 10 figures

While large language models (LLMs) have demonstrated exceptional performance in recent natural language processing (NLP) tasks, their deployment poses substantial challenges due to high computational and memory demands in real-world applications. Recent studies have focused on enhancing smaller models through knowledge distillation from LLMs, yielding promising results. However, these models often struggle to match the performance of LLMs, especially in tasks that require reasoning. In this work, we introduce Mixed Distillation (MD) framework, which capitalizes on the strengths of Program of Thought (PoT) and Chain of Thought (CoT) capabilities within LLMs, combining multiple prompting techniques and distilling these capabilities into smaller models. Our experimental results show that MD significantly enhances the single-path and multi-path reasoning ability of smaller models in various tasks. In terms of accuracy and generality of reasoning tasks, the model generated by it exceeds the comprehensive performance of two individually distilled models. Notably, LLaMA2-7B and CodeLlama-7B using MD achieved remarkable improvements of (84.5%) and (85.5%), respectively, outperforming GPT-3.5-Turbo by (2.5%) and (3.5%), on the SVAMP benchmark., Comment: Working in Progress, 17 pages, 16 figures

Since its introduction in 2017, Transformer has emerged as the leading neural network architecture, catalyzing revolutionary advancements in many AI disciplines. The key innovation in Transformer is a Self-Attention (SA) mechanism designed to capture contextual information. However, extending the original Transformer design to models of greater depth has proven exceedingly challenging, if not impossible. Even though various modifications have been proposed in order to stack more layers of SA mechanism into deeper models, a full understanding of this depth problem remains lacking. In this paper, we conduct a comprehensive investigation, both theoretically and empirically, to substantiate the claim that the depth problem is caused by \emph{token similarity escalation}; that is, tokens grow increasingly alike after repeated applications of the SA mechanism. Our analysis reveals that, driven by the invariant leading eigenspace and large spectral gaps of attention matrices, token similarity provably escalates at a linear rate. Based on the gained insight, we propose a new strategy of surgically removing excessive similarity in contrast to the existing approach of diminishing the SA mechanism explicitly or implicitly (such as in pre-norm transformers). Preliminary experimental results confirm the effectiveness of the proposed strategy in small-scale post-norm Transformer models.

Recently, several new solar radio telescopes have been put into operation and provided spectral-imaging observations with much higher resolutions in decimeter (dm) and centimeter (cm) wavelengths. These telescopes include the Mingantu Spectral Radioheliograph (MUSER, at frequencies of 0.4 - 15 GHz), the Expanded Owens Valley Solar Array (EOVSA, at frequencies of 1 - 18 GHz), and the Siberian Radio Heliograph (SRH, at frequencies of 3 - 24 GHz). These observations offer unprecedented opportunities to study solar physics and space weather, especially to diagnose the coronal magnetic fields, reveal the basic nature of solar eruptions and the related non-thermal energy release, particle accelerations and propagation, and the related emission mechanisms. These results might be the important input to the space weather modeling for predicting the occurrence of disastrous powerful space weather events. In order to provide meaningful reference for other solar physicists and space weather researchers, this paper mainly focus on discussing the potential scientific problems of solar radio spectral-imaging observations in dm-cm wavelengths and its possible applications in the field of space weather. These results will provide a helpful reference for colleagues to make full use of the latest and future observation data obtained from the above solar radio telescopes., Comment: 10 pages, 7 figures, accepted by Advance in Space Research, 2022

In task-oriented dialogue scenarios, cross-domain zero-shot slot filling plays a vital role in leveraging source domain knowledge to learn a model with high generalization ability in unknown target domain where annotated data is unavailable. However, the existing state-of-the-art zero-shot slot filling methods have limited generalization ability in target domain, they only show effective knowledge transfer on seen slots and perform poorly on unseen slots. To alleviate this issue, we present a novel Hierarchical Contrastive Learning Framework (HiCL) for zero-shot slot filling. Specifically, we propose a coarse- to fine-grained contrastive learning based on Gaussian-distributed embedding to learn the generalized deep semantic relations between utterance-tokens, by optimizing inter- and intra-token distribution distance. This encourages HiCL to generalize to the slot types unseen at training phase. Furthermore, we present a new iterative label set semantics inference method to unbiasedly and separately evaluate the performance of unseen slot types which entangled with their counterparts (i.e., seen slot types) in the previous zero-shot slot filling evaluation methods. The extensive empirical experiments on four datasets demonstrate that the proposed method achieves comparable or even better performance than the current state-of-the-art zero-shot slot filling approaches., Comment: Accepted by Findings of EMNLP2023 as a long paper

Commonsense reasoning is a pivotal skill for large language models, yet it presents persistent challenges in specific tasks requiring this competence. Traditional fine-tuning approaches can be resource-intensive and potentially compromise a model's generalization capacity. Furthermore, state-of-the-art language models like GPT-3.5 and Claude are primarily accessible through API calls, which makes fine-tuning models challenging. To address these challenges, we draw inspiration from the outputs of large models for tailored tasks and semi-automatically developed a set of novel prompts from several perspectives, including task-relevance, supportive evidence generation (e.g. chain-of-thought and knowledge), diverse path decoding to aid the model. Experimental results on ProtoQA dataset demonstrate that with better designed prompts we can achieve the new state-of-art(SOTA) on the ProtoQA leaderboard, improving the Max Answer@1 score by 8%, Max Incorrect@1 score by 4% (breakthrough 50% for the first time) compared to the previous SOTA model and achieved an improvement on StrategyQA and CommonsenseQA2.0 (3% and 1%, respectively). Furthermore, with the generated Chain-of-Thought and knowledge, we can improve the interpretability of the model while also surpassing the previous SOTA models. We hope that our work can provide insight for the NLP community to develop better prompts and explore the potential of large language models for more complex reasoning tasks.

Maritime surveillance is not only necessary for every country, such as in maritime safeguarding and fishing controls, but also plays an essential role in international fields, such as in rescue support and illegal immigration control. Most of the existing automatic target recognition (ATR) methods directly send the extracted whole features of SAR ships into one classifier. The classifiers of most methods only assign one feature center to each class. However, the characteristics of SAR ship images, large inner-class variance, and small interclass difference lead to the whole features containing useless partial features and a single feature center for each class in the classifier failing with large inner-class variance. We proposes a SAR ship target recognition method via selective feature discrimination and multifeature center classifier. The selective feature discrimination automatically finds the similar partial features from the most similar interclass image pairs and the dissimilar partial features from the most dissimilar inner-class image pairs. It then provides a loss to enhance these partial features with more interclass separability. Motivated by divide and conquer, the multifeature center classifier assigns multiple learnable feature centers for each ship class. In this way, the multifeature centers divide the large inner-class variance into several smaller variances and conquered by combining all feature centers of one ship class. Finally, the probability distribution over all feature centers is considered comprehensively to achieve an accurate recognition of SAR ship images. The ablation experiments and experimental results on OpenSARShip and FUSAR-Ship datasets show that our method has achieved superior recognition performance under decreasing training SAR ship samples.

Existing synthetic aperture radar automatic target recognition (SAR ATR) methods have been effective for the classification of seen target classes. However, it is more meaningful and challenging to distinguish the unseen target classes, i.e., open set recognition (OSR) problem, which is an urgent problem for the practical SAR ATR. The key solution of OSR is to effectively establish the exclusiveness of feature distribution of known classes. In this letter, we propose an entropy-awareness meta-learning method that improves the exclusiveness of feature distribution of known classes which means our method is effective for not only classifying the seen classes but also encountering the unseen other classes. Through meta-learning tasks, the proposed method learns to construct a feature space of the dynamic-assigned known classes. This feature space is required by the tasks to reject all other classes not belonging to the known classes. At the same time, the proposed entropy-awareness loss helps the model to enhance the feature space with effective and robust discrimination between the known and unknown classes. Therefore, our method can construct a dynamic feature space with discrimination between the known and unknown classes to simultaneously classify the dynamic-assigned known classes and reject the unknown classes. Experiments conducted on the moving and stationary target acquisition and recognition (MSTAR) dataset have shown the effectiveness of our method for SAR OSR.

Maritime surveillance is indispensable for civilian fields, including national maritime safeguarding, channel monitoring, and so on, in which synthetic aperture radar (SAR) ship target recognition is a crucial research field. The core problem to realizing accurate SAR ship target recognition is the large inner-class variance and inter-class overlap of SAR ship features, which limits the recognition performance. Most existing methods plainly extract multi-scale features of the network and utilize equally each feature scale in the classification stage. However, the shallow multi-scale features are not discriminative enough, and each scale feature is not equally effective for recognition. These factors lead to the limitation of recognition performance. Therefore, we proposed a SAR ship recognition method via multi-scale feature attention and adaptive-weighted classifier to enhance features in each scale, and adaptively choose the effective feature scale for accurate recognition. We first construct an in-network feature pyramid to extract multi-scale features from SAR ship images. Then, the multi-scale feature attention can extract and enhance the principal components from the multi-scale features with more inner-class compactness and inter-class separability. Finally, the adaptive weighted classifier chooses the effective feature scales in the feature pyramid to achieve the final precise recognition. Through experiments and comparisons under OpenSARship data set, the proposed method is validated to achieve state-of-the-art performance for SAR ship recognition.

Without sufficient data, the quantity of information available for supervised training is constrained, as obtaining sufficient synthetic aperture radar (SAR) training data in practice is frequently challenging. Therefore, current SAR automatic target recognition (ATR) algorithms perform poorly with limited training data availability, resulting in a critical need to increase SAR ATR performance. In this study, a new method to improve SAR ATR when training data are limited is proposed. First, an embedded feature augmenter is designed to enhance the extracted virtual features located far away from the class center. Based on the relative distribution of the features, the algorithm pulls the corresponding virtual features with different strengths toward the corresponding class center. The designed augmenter increases the amount of information available for supervised training and improves the separability of the extracted features. Second, a dynamic hierarchical-feature refiner is proposed to capture the discriminative local features of the samples. Through dynamically generated kernels, the proposed refiner integrates the discriminative local features of different dimensions into the global features, further enhancing the inner-class compactness and inter-class separability of the extracted features. The proposed method not only increases the amount of information available for supervised training but also extracts the discriminative features from the samples, resulting in superior ATR performance in problems with limited SAR training data. Experimental results on the moving and stationary target acquisition and recognition (MSTAR), OpenSARShip, and FUSAR-Ship benchmark datasets demonstrate the robustness and outstanding ATR performance of the proposed method in response to limited SAR training data.

Although deep learning-based methods have achieved excellent performance on SAR ATR, the fact that it is difficult to acquire and label a lot of SAR images makes these methods, which originally performed well, perform weakly. This may be because most of them consider the whole target images as input, but the researches find that, under limited training data, the deep learning model can't capture discriminative image regions in the whole images, rather focus on more useless even harmful image regions for recognition. Therefore, the results are not satisfactory. In this paper, we design a SAR ATR framework under limited training samples, which mainly consists of two branches and two modules, global assisted branch and local enhanced branch, feature capture module and feature discrimination module. In every training process, the global assisted branch first finishes the initial recognition based on the whole image. Based on the initial recognition results, the feature capture module automatically searches and locks the crucial image regions for correct recognition, which we named as the golden key of image. Then the local extract the local features from the captured crucial image regions. Finally, the overall features and local features are input into the classifier and dynamically weighted using the learnable voting parameters to collaboratively complete the final recognition under limited training samples. The model soundness experiments demonstrate the effectiveness of our method through the improvement of feature distribution and recognition probability. The experimental results and comparisons on MSTAR and OPENSAR show that our method has achieved superior recognition performance.

Synthetic aperture radar automatic target recognition (SAR ATR) with limited data has recently been a hot research topic to enhance weak generalization. Despite many excellent methods being proposed, a fundamental theory is lacked to explain what problem the limited SAR data causes, leading to weak generalization of ATR. In this paper, we establish a causal ATR model demonstrating that noise $N$ that could be blocked with ample SAR data, becomes a confounder with limited data for recognition. As a result, it has a detrimental causal effect damaging the efficacy of feature $X$ extracted from SAR images, leading to weak generalization of SAR ATR with limited data. The effect of $N$ on feature can be estimated and eliminated by using backdoor adjustment to pursue the direct causality between $X$ and the predicted class $Y$. However, it is difficult for SAR images to precisely estimate and eliminated the effect of $N$ on $X$. The limited SAR data scarcely powers the majority of existing optimization losses based on empirical risk minimization (ERM), thus making it difficult to effectively eliminate $N$'s effect. To tackle with difficult estimation and elimination of $N$'s effect, we propose a dual invariance comprising the inner-class invariant proxy and the noise-invariance loss. Motivated by tackling change with invariance, the inner-class invariant proxy facilitates precise estimation of $N$'s effect on $X$ by obtaining accurate invariant features for each class with the limited data. The noise-invariance loss transitions the ERM's data quantity necessity into a need for noise environment annotations, effectively eliminating $N$'s effect on $X$ by cleverly applying the previous $N$'s estimation as the noise environment annotations. Experiments on three benchmark datasets indicate that the proposed method achieves superior performance.