Potential Loss Of Information Research Articles

Automated MRI pituitary structured reporting from free-text using a fine-tuned Llama model: a feasibility study.

Structured reports in radiology have demonstrated substantial advantages over unstructured ones. However, the transition from unstructured to structured reporting can face challenges, as experienced radiologists worry about the potential loss of valuable information. In this study, we fine-tuned the Llama 2 model capable of generating structured pituitary MRI reports from unstructured reports. We used a training set comprising 104 pituitary MRI reports to fine-tune Llama 2 and 26 reports as a test set to evaluate the system. The dataset was annotated manually by three expert radiologists. For this annotation, the radiologists used the unstructured report and structured it into eight anatomical landmarks: adenohypophysis, pituitary stalk, optic chiasm, suprasellar cistern, neurohypophysis, cavernous sinuses, sphenoid sinuses and other findings. Llama2 achieves a value greater than 0.79 on the ROUGE-L metric in four anatomical landmarks from free-text pituitary MRI reports. The other anatomical landmarks exceed 0.61 of ROUGE-L except for the other findings section. Our study suggests good performance in structuring anatomical landmarks on pituitary MRI reports using the fine-tune Llama 2 model.

DeepNeXt: a lightweight polyp segmentation algorithm based on multi-scale attention.

Fast and accurate automatic segmentation of polyps in colonoscopy plays a crucial role in the early diagnosis and treatment of colon cancer. However, the current polyp segmentation algorithms based on deep neural networks suffer from the problems of larger models and lower segmentation accuracy. Meanwhile, achieving accurate segmentation of polyps is to improve the diagnostic efficiency of doctors, and this need motivates us to develop a set of lightweight models so that it can be easily embedded in clinical devices to meet the requirements of practical applications. This study aims to provide effective technical support for the rapid and precise segmentation of polyps in clinical applications. DeepNeXt, an innovative polyp segmentation model grounded in multi-scale attention mechanisms. DeepNeXt incorporates a multi-stage, lightweight convolutional encoder module, leveraging several lightweight convolutional layers for efficient and accurate feature extraction. Furthermore, it features a novel multi-stage feature fusion structure designed to circumvent the potential loss of feature information during the encoding phase. Additionally, the model employs a multi-scale attentional feature encoding module that harnesses multi-branch deep strip convolution techniques to extract multi-dimensional information from the feature maps post-encoding, thereby enhancing the neural network's capability to extract diverse feature information. Experimental validation on the Kvasir Segmentation Dataset (Kvasir-SEG dataset) and Colorectal Cancer-Clinic Datasetbase (CVC-ClinicDB datasets) demonstrates that DeepNeXt outperforms mainstream networks such as U-net, U-net++, TransUnet, SwinUnet, and TGANet in terms of parameters and floating-point operations (FLOPs). DeepNeXt achieved a FLOPs metric of only 3.04 G and a parameters (Params) metric of just 1.51 M, while delivering exceptional performance in segmentation. On the Kvasir-SEG dataset, it reached a mean intersection over union (mIOU) of 83.91, and on the CVC-ClinicDB dataset, 87.37. Additionally, the Dice and Recall metrics also showed superior results, highlighting that DeepNeXt strikes an optimal balance between computational efficiency, model compactness, and segmentation accuracy. In conclusion, we have proposed the DeepNeXt network, a novel lightweight multi-scale attention segmentation network tailored for computationally limited medical devices, which provides strong support for accurate and efficient polyp segmentation in clinical applications.

Multimodal Cross-Lingual Summarization for Videos: A Revisit in Knowledge Distillation Induced Triple-Stage Training Method.

Multimodal summarization (MS) for videos aims to generate summaries from multi-source information (e.g., video and text transcript), showing promising progress recently. However, existing works are limited to monolingual scenarios, neglecting non-native viewers' needs to understand videos in other languages. It stimulates us to introduce multimodal cross-lingual summarization for videos (MCLS), which aims to generate cross-lingual summaries from multimodal input of videos. Considering the challenge of high annotation cost and resource constraints in MCLS, we propose a knowledge distillation (KD) induced triple-stage training method to assist MCLS by transferring knowledge from abundant monolingual MS data to those data with insufficient volumes. In the triple-stage training method, a video-guided dual fusion network (VDF) is designed as the backbone network to integrate multimodal and cross-lingual information through diverse fusion strategies in the encoder and decoder; What's more, we propose two cross-lingual knowledge distillation strategies: adaptive pooling distillation and language-adaptive warping distillation (LAWD), designed for encoder-level and vocab-level distillation objects to facilitate effective knowledge transfer across cross-lingual sequences of varying lengths between MS and MCLS models. Specifically, to tackle lingual sequences of varying lengths between MS and MCLS models. Specifically, to tackle the challenge of unequal length of parallel cross-language sequences in KD, LAWD can directly conduct cross-language distillation while keeping the language feature shape unchanged to reduce potential information loss. We meticulously annotated the How2-MCLS dataset based on the How2 dataset to simulate MCLS scenarios. Experimental results show that the proposed method achieves competitive performance compared to strong baselines, and can bring substantial performance improvements to MCLS models by transferring knowledge from the MS model.

Sample Inflation Interpolation for Consistency Regularization in Remote Sensing Change Detection

Semi-supervised learning has gained significant attention in the field of remote sensing due to its ability to effectively leverage both a limited number of labeled samples and a large quantity of unlabeled data. An effective semi-supervised learning approach utilizes unlabeled samples to enforce prediction consistency under minor perturbations, thus reducing the model’s sensitivity to noise and suppressing false positives in change-detection tasks. This principle underlies consistency regularization-based methods. However, while these methods enhance noise robustness, they also risk overlooking subtle but meaningful changes, leading to information loss and missed detections. To address this issue, we introduce a simple yet efficient method called Sample Inflation Interpolation (SII). This method leverages labeled sample pairs to mitigate the information loss caused by consistency regularization. Specifically, we propose a novel data augmentation strategy that generates additional change samples by combining existing supervised change samples with calculated proportions of change areas. This approach increases both the quantity and diversity of change samples in the training set, effectively compensating for potential information loss and reducing missed detections. Furthermore, to prevent overfitting, small perturbations are applied to the generated sample pairs and their labels. Experiments conducted on two public change detection (CD) datasets validate the effectiveness of our proposed method. Remarkably, even with only 5% of labeled training data, our method achieves performance levels that closely approach those of fully supervised learning models.

Modeling takeover time for non-driving related tasks using hybrid deep neural networks in conditionally automated vehicles

To enhance the safety of the transition from autonomous to manual driving control, one of the key factors is quantifying the safe takeover transition, namely the takeover time. Previous studies have focused on factors influencing takeover time and predicting takeover time using traditional methods, but there is a lack of research utilizing deep learning networks and driver physiological factors for takeover time prediction. Toward this end, we propose a hybrid deep learning network model dedicated to predicting drivers’ takeover time with a dataset obtained from a bench experiment involving 46 drivers. Firstly, to address the potential information loss commonly associated with traditional manual feature extraction techniques, a convolutional neural network (CNN) is developed to automatically extract physiological spatial representations from drivers. Additionally, a double-layer bidirectional long short-term memory network (DBiLSTM) is incorporated to model the physiological time representation dimension, enabling a more refined representation of physiological signals. Then, to tackle the complexities introduced by individual driver variations, a self-attention mechanism is enabling the model to automatically prioritize critical features, thereby enhancing the accuracy and reliability of its predictions. The results demonstrate that the proposed approach surpasses traditional machine learning network models in predictive accuracy for takeover time prediction, thereby exhibiting novelty in the field of vehicle takeover control research. This provides a more reliable technical foundation for anticipating the durations of vehicle takeovers.

Multi-feature enhancement based on sparse networks for single-stage 3D object detection

In the field of autonomous driving, the accuracy and real-time requirements for 3D object detection technology continue to improve, which is directly related to the commercialization process and market popularity of autonomous vehicles. Despite the efficiency of pillar-based coding for onboard systems, it falls short in terms of accuracy and the reduction of incorrect positives. In this paper, we will examine how to solve the problem of high incorrect rate and low accuracy of existing methods. Firstly, a MAP coding module is introduced to optimize previous point cloud feature coding modules, allowing for the efficient extraction of fine-grained features from point cloud data. Then, we introduce an innovative sparse dual attention (SDA) to efficiently filter out irrelevant details in feature extraction, thereby improving the pertinence and efficiency of information extraction. Finally, to address the potential loss of information from single local feature extraction, a local and global fusion module (CTGC) is introduced. Our method has proactively demonstrated its efficiency and accuracy through rigorous experimentation across diverse datasets. Analysis of the results leads to the conclusion that our solutions provide accurate and robust detection results. Code will be available at https://github.com/lcy199905/MyOpenPCDet.git.

Uncovering condition information loss in medical text extraction: The challenge of non-contiguous spans

We investigated the limitations of conventional named entity recognition (NER) and entity linking (EL) methods in accurately extracting patient condition information from medical texts, focusing on the challenges posed by non-contiguous spans and the potential information loss. We utilized a corpus with entity-relation annotations, analyzing the frequency and nature of non-contiguous spans that include irrelevant entities within gaps. The corpus was further analyzed to pinpoint the types of entity representations predominantly linked with peripheral spans—those not encompassing central symptom-describing terms—with a focus on items, body parts, and clinical tests. Our analysis revealed that 18.6 % of patient condition expressions were non-contiguous spans containing irrelevant entities, suggesting an accuracy ceiling of 81.4 % for conventional NER and EL approaches in the worst-case scenario. The study highlights the importance of entity types such as items, body parts, and clinical tests in these expressions, indicating that conventional extraction methods incur considerable information loss. The findings underscore the need for more sophisticated information extraction techniques capable of handling the complexities of medical texts, including non-contiguous spans. Adapting methods that allow gaps within entities or employing graph-based term assignments can enhance the accuracy and comprehensiveness of medical text annotation.

Structural and Dynamical Quality Assessment of Gap‐Filled Sea Surface Temperature Products

AbstractPrevious studies that intercompared global Level‐4 (L4) sea surface temperature (SST) analyses were centered on the assessment of the accuracy and bias of SST by comparing them with independent near‐surface Argo profile temperature data. This type of assessment is centered on the absolute value of SST rather than on SST spatial properties (gradients), which is more relevant to the study of oceanographic features (e.g., fronts, eddies, etc.) and ocean dynamics. Here, we use, for the first time, the spectrum of singularity exponents to assess the structural and dynamical quality of different L4 gap‐filled products based on the multifractal theory of turbulence. Singularity exponents represent the geometrical projection of the turbulence cascade, and its singular spectrum can be related to the probability density function of the singularity exponents normalized by the scale. Our results reveal that the different schemes used to produce the L4 SST products generate different singularity spectra, which are then used to identify a potential loss of dynamical information or structural coherence. This new diagnostic constitutes a valuable tool to assess the structural quality of SST products and can support data satellite SST producers efforts to improve the interpolation schemes used to generate gap‐filled SST products.

Research on a Method for Identification of Peanut Pests and Diseases Based on a Lightweight LSCDNet Model.

Timely and accurate identification of peanut pests and diseases, coupled with effective countermeasures, is pivotal for ensuring high-quality and efficient peanut production. Despite the prevalence of pests and diseases in peanut cultivation, challenges such as minute disease spots, the elusive nature of pests, and intricate environmental conditions often lead to diminished identification accuracy and efficiency. Moreover, continuous monitoring of peanut health in real-world agricultural settings demands solutions that are computationally efficient. Traditional deep learning models often require substantial computational resources, limiting their practical applicability. In response to these challenges, we introduce LSCDNet (Lightweight Sandglass and Coordinate Attention Network), a streamlined model derived from DenseNet. LSCDNet preserves only the transition layers to reduce feature map dimensionality, simplifying the model's complexity. The inclusion of a sandglass block bolsters features extraction capabilities, mitigating potential information loss due to dimensionality reduction. Additionally, the incorporation of coordinate attention addresses issues related to positional information loss during feature extraction. Experimental results showcase that LSCDNet achieved impressive metrics with accuracy, precision, recall, and Fl score of 96.67, 98.05, 95.56, and 96.79%, respectively, while maintaining a compact parameter count of merely 0.59 million. When compared with established models such as MobileNetV1, MobileNetV2, NASNetMobile, DenseNet-121, InceptionV3, and X-ception, LSCDNet outperformed with accuracy gains of 2.65, 4.87, 8.71, 5.04, 6.32, and 8.2%, respectively, accompanied by substantially fewer parameters. Lastly, we deployed the LSCDNet model on Raspberry Pi for practical testing and application and achieved an average recognition accuracy of 85.36%, thereby meeting real-world operational requirements.

Multi-level feature interaction for open knowledge base canonicalization

Open Information Extraction (OpenIE) aims to construct expansive open knowledge bases (OKBs) by extracting triples (noun phrase, relation phrase, noun phrase) from unstructured text. One critical problem in OKBs is the lack of canonicalization for noun phrases and relation phrases, leading to the storage of redundant and ambiguous facts. Consequently, open knowledge base canonicalization, which clusters synonymous phrases into the same group, has emerged as an active research area. Existing approaches either leverage fact triples or source context in isolation, or at best, interact them at the clustering level. However, these approaches lack explicit interaction or only loosely couple the two types of knowledge, resulting in the potential loss of valuable intermediate information. In this paper, we propose MuFIC, a novel unsupervised framework that interacts the fact triples and source context at the feature level to address these limitations. In order to capture and integrate fine-grained fact and context knowledge, we design three levels of feature interaction: low-level context-guided feature interaction, mid-level fact-guided feature interaction, and high-level gated fusion feature interaction. Furthermore, we introduce an additional objective function via contrastive learning to improve the quality of extracted features and reduce knowledge-specific noise. Finally, we design a bidirectional feedback mechanism to better guide the learning process of joint features by harnessing side information prototype learning, and to dynamically optimize side information based on the clustering results formed by joint features. Extensive experiments on three public benchmark datasets demonstrate the superiority of our proposed framework.

Retina Blood Vessels Segmentation and Classification with the Multi-featured Approach.

Segmenting retinal blood vessels poses a significant challenge due to the irregularities inherent in small vessels. The complexity arises from the intricate task of effectively merging features at multiple levels, coupled with potential spatial information loss during successive down-sampling steps. This particularly affects the identification of small and faintly contrasting vessels. To address these challenges, we present a model tailored for automated arterial and venous (A/V) classification, complementing blood vessel segmentation. This paper presents an advanced methodology for segmenting and classifying retinal vessels using a series of sophisticated pre-processing and feature extraction techniques. The ensemble filter approach, incorporating Bilateral and Laplacian edge detectors, enhances image contrast and preserves edges. The proposed algorithm further refines the image by generating an orientation map. During the vessel extraction step, a complete convolution network processes the input image to create a detailed vessel map, enhanced by attention operations that improve modeling perception and resilience. The encoder extracts semantic features, while the Attention Module refines blood vessel depiction, resulting in highly accurate segmentation outcomes. The model was verified using the STARE dataset, which includes 400 images; the DRIVE dataset with 40 images; the HRF dataset with 45 images; and the INSPIRE-AVR dataset containing 40 images. The proposed model demonstrated superior performance across all datasets, achieving an accuracy of 97.5% on the DRIVE dataset, 99.25% on the STARE dataset, 98.33% on the INSPIREAVR dataset, and 98.67% on the HRF dataset. These results highlight the method's effectiveness in accurately segmenting and classifying retinal vessels.

Phage Display Panning on Silica: Optimization of Elution Conditions for Selection of Strong Binders.

Phage display panning is a powerful tool to select strong peptide binders to a given target, and when applied to inorganic materials (e.g., silica) as a target, it provides information on binding events and molecular recognition at the peptide-mineral interface. The panning process has limitations with the phage chemical elution being affected by bias toward positively charged binders, resulting in the potential loss of information on binder diversity; the presence of fast growing phages with an intrinsic growth advantage; and the presence of false positives from target unrelated peptides. To overcome some of these limitations, we developed a panning approach based on the sequential use of different eluents (Gly-HCl, pH-2.2; MgCl2, pH-6.1; and TEA, pH-11.0), or pH conditions (Gly-HCl 2.2 < pH < 11.0) that allows the identification of a diverse and comprehensive pool of strong binders. We have assessed and tested the authenticity of the identified silica binders via a complementary experimental (in vivo phage recovery rates and TEM imaging) and bioinformatics approach. We provide experimental evidence of the nonspecificity of the Gly-HCl eluent as typically used. Using a fluorimetric assay, we investigate in vitro binding of two peptides that differ by pI-S4 (HYIDFRW, pI 7.80) and S5 (YSLKQYQ, pI 9.44)─modified at the C terminal with an amide group to simulate net charges in the phage display system, confirming the vital role of electrostatic interactions as driving binding forces in the phage panning process. The presented optimized phage panning approach provides an opportunity to match known surface interactions at play with suitable elution conditions; to select only sequences relevant to a particular interfacial system. The approach has the potential to open up avenues to design interfacial systems to advance our understanding of peptide-assisted mineral growth, among other possibilities.

Validation of the Maslach Burnout Inventory-General Survey 9-item short version: psychometric properties and measurement invariance across age, gender, and continent.

The Maslach Burnout Inventory-General Survey (MBI-GS) stands as the preeminent tool for assessing burnout across various professions. Although the MBI-GS9 emerged as a derivative of the MBI-GS and has seen extensive use over several years, a comprehensive examination of its psychometric properties has yet to be undertaken. This study followed the Standards for Educational and Psychological Testing guidelines to validate the MBI-GS9. Employing a combined approach of classical test theory and item response theory, particularly Rasch analysis, within an integrated framework, the study analyzed data from 16,132 participants gathered between 2005 and 2015 by the Centre for Organizational Research at Acadia University. The findings revealed that the MBI-GS9 exhibited satisfactory reliability and validity akin to its predecessor, the MBI-GS. Across its three dimensions, Cronbach's α and omega coefficients ranged from 0.84 to 0.91. Notably, the MBI-GS9 displayed no floor/ceiling effects and demonstrated good item fit, ordered threshold, acceptable person and item separation and reliability, clear item difficulty hierarchy, and a well-distributed item threshold. However, the results suggested a recommended minimum sample size of 350 to mitigate potential information loss when employing the MBI-GS9. Beyond this threshold, the observed mean difference between the MBI-GS and MBI-GS9 held minimal practical significance. Furthermore, measurement equivalence tests indicated that the MBI-GS9 maintained an equivalent three-factor structure and factor loadings across various gender, age, and continent groups, albeit with inequivalent latent values across continents. In sum, the MBI-GS9 emerges as a reliable and valid alternative to the MBI-GS, particularly when utilized within large, diverse samples across different age and gender demographics. However, to address potential information loss, a substantial sample size is recommended when employing the MBI-GS9. In addition, for cross-cultural comparisons, it is imperative to initially assess equivalence across different language versions at both the item and scale levels.

CFE-YOLOv8s: Improved YOLOv8s for Steel Surface Defect Detection

Due to the low detection accuracy in steel surface defect detection and the constraints of limited hardware resources, we propose an improved model for steel surface defect detection, named CBiF-FC-EFC-YOLOv8s (CFE-YOLOv8s), including CBS-BiFormer (CBiF) modules, Faster-C2f (FC) modules, and EMA-Faster-C2f (EFC) modules. Firstly, because of the potential information loss that convolutional neural networks (CNN) may encounter when dealing with miniature targets, the CBiF combines CNN with Transformer to optimize local and global features. Secondly, to address the increased computational complexity caused by the extensive use of convolutional layers, the FC uses the FasterNet block to reduce redundant computations and memory access. Lastly, the EMA is incorporated into the FC to design the EFC module and enhance feature fusion capability while ensuring the light weight of the model. CFE-YOLOv8s achieves mAP@0.5 values of 77.8% and 69.5% on the NEU-DET and GC10-DET datasets, respectively, representing enhancements of 3.1% and 2.8% over YOLOv8s, with reductions of 22% and 18% in model parameters and FLOPS. The CFE-YOLOv8s demonstrates superior overall performance and balance compared to other advanced models.

Research on Feature Fusion Method Based on Graph Convolutional Networks

This paper proposes an enhanced BertGCN-Fusion (BGF) model aimed at addressing the limitations of Graph Convolutional Networks (GCN) in processing global text features for text categorization tasks. While traditional GCN effectively capture local structural features, they face challenges when integrating global semantic features. Issues such as the potential loss of global semantic information due to local feature fusion and limited depth of information propagation are prevalent. To overcome these challenges, the BGF model introduces improvements based on the BertGCN framework: (1) Feature fusion mechanism: Introducing a linear layer to fuse BERT outputs with traditional features facilitates the integration of fine-grained local semantic features from BERT with traditional global features. (2) Multilayer fusion approach: Employing a multilayer fusion technique enhances the integration of textual semantic features, thereby comprehensively and accurately capturing text semantic information. Experimental results demonstrate that the BGF model achieves notable performance improvements across multiple datasets. On the R8 and R52 datasets, the BGF model achieves accuracies of 98.45% and 93.77%, respectively, marking improvements of 0.28% to 0.90% compared to the BertGCN model. These findings highlight the BGF model’s efficacy in overcoming the deficiencies of traditional GCN in processing global semantic features, presenting an efficient approach for handling text data.

CNN-Based Machine Tool Monitoring with STFT Image Analysis

Abstract: In the realm of machine tool operation, effective condition monitoring holds predominant importance to ensure operational reliability and safety. Leveraging deep learning methodologies, particularly convolutional neural networks (CNN), for defect identification has gained significant attention. However, inherent challenges persist, including the extraction of salient features and potential information loss while extracting the features from raw vibration signals. In response, this study proposes an intelligent approach for condition monitoring in machine tools, integrating short-time Fourier transform and convolutional neural networks (STFT-CNN). The process entails using STFT to convert one-dimensional vibration signals into time-frequency pictures, which are then fed into the STFT-CNN model to acquire and identify fault features. Furthermore, the study explores optimizing STFT parameters, such as window type, window width, and translation overlap width, across various typical window functions to improve the effectiveness of the transformation process. Within the STFT-CNN model, the utilization of stacked double convolutional layers aims to augment the model's nonlinear expression capacity, thereby facilitating robust fault diagnosis capabilities in machine tool condition monitoring applications

Bioinspired In-Sensor Multimodal Fusion for Enhanced Spatial and Spatiotemporal Association.

Multimodal perception can capture more precise and comprehensive information compared with unimodal approaches. However, current sensory systems typically merge multimodal signals at computing terminals following parallel processing and transmission, which results in the potential loss of spatial association information and requires time stamps to maintain temporal coherence for time-series data. Here we demonstrate bioinspired in-sensor multimodal fusion, which effectively enhances comprehensive perception and reduces the level of data transfer between sensory terminal and computation units. By adopting floating gate phototransistors with reconfigurable photoresponse plasticity, we realize the agile spatial and spatiotemporal fusion under nonvolatile and volatile photoresponse modes. To realize an optimal spatial estimation, we integrate spatial information from visual-tactile signals. For dynamic events, we capture and fuse in real time spatiotemporal information from visual-audio signals, realizing a dance-music synchronization recognition task without a time-stamping process. This in-sensor multimodal fusion approach provides the potential to simplify the multimodal integration system, extending the in-sensor computing paradigm.

FDR-MSA: Enhancing multimodal sentiment analysis through feature disentanglement and reconstruction

Multimodal sentiment analysis (MSA) is crucial as it integrates textual, visual, and audio information from videos to accurately identify human emotional states. This study proposes an innovative multimodal feature decoupling strategy that categorizes sentiment features into common and private features. The private features aim to accurately capture the uniqueness of each modality, thereby increasing feature diversity. In contrast, the common features seek to identify and capture commonalities among different modalities, thus reducing potential information loss during decoupling. To achieve this, we designed dedicated encoders and loss function constraints for both types of features. Additionally, to mitigate information redundancy and prevent key information loss during decoupled representation learning, we introduce a dual feature reconstruction mechanism comprising unimodal feature reconstruction (UFR) and multimodal feature reconstruction (MFR). These mechanisms preserve vital information from the decoupling process and mitigate the impact of redundant data. Our extensive experiments on three datasets demonstrate that our method achieves a significant margin of approximately 1%–3% in accuracy, illustrating that our approach outperforms existing advanced techniques significantly, resulting in noteworthy performance enhancements.

RFI-DRUnet: Restoring dynamic spectra corrupted by radio frequency interference—Application to pulsar observations

Radio frequency interference (RFI) has been an enduring concern in radio astronomy, particularly for the observations of pulsars which require high timing precision and data sensitivity. In most works of the literature, RFI mitigation has been formulated as a detection task that consists of localizing possible RFI in dynamic spectra. This strategy inevitably leads to a potential loss of information since parts of the signal identified as possibly RFI-corrupted are generally not considered in the subsequent data processing pipeline. Conversely, this work proposes to tackle RFI mitigation as a joint detection and restoration that allows parts of the dynamic spectrum affected by RFI to be not only identified but also recovered. The proposed supervised method relies on a deep convolutional network whose architecture inherits the performance reached by a recent yet popular image-denoising network. To train this network, a whole simulation framework is built to generate large data sets according to physics-inspired and statistical models of the pulsar signals and of the RFI. The relevance of the proposed approach is quantitatively assessed by conducting extensive experiments. In particular, the results show that the restored dynamic spectra are sufficiently reliable to estimate pulsar times-of-arrivals with an accuracy close to the one that would be obtained from RFI-free signals.

Multistage Interaction Network for Remote Sensing Change Detection

Change detection in remote sensing imagery is vital for Earth monitoring but faces challenges such as background complexity and pseudo-changes. Effective interaction between bitemporal images is crucial for accurate change information extraction. This paper presents a multistage interaction network designed for effective change detection, incorporating interaction at the image, feature, and decision levels. At the image level, change information is directly extracted from intensity changes, mitigating potential change information loss during feature extraction. Instead of separately extracting features from bitemporal images, the feature-level interaction jointly extracts features from bitemporal images. By enhancing relevance to spatial variant information and shared semantic channels, the network excels in overcoming background complexity and pseudo-changes. The decision-level interaction combines image-level and feature-level interactions, producing multiscale feature differences for precise change prediction. Extensive experiments demonstrate the superior performance of our method compared to existing approaches, establishing it as a robust solution for remote sensing image change detection.