Adaptive Feature Research Articles

GF-UNet:A Cropland Extraction Method Based on Attention Gate and Adaptive Feature Fusion

GF-UNet:A Cropland Extraction Method Based on Attention Gate and Adaptive Feature Fusion

UAV Complex-Scene Single-Target Tracking Based on Improved Re-Detection Staple Algorithm

With the advancement of remote sensing technology, the demand for the accurate monitoring and tracking of various targets utilizing unmanned aerial vehicles (UAVs) is increasing. However, challenges such as object deformation, motion blur, and object occlusion during the tracking process could significantly affect tracking performance and ultimately lead to tracking drift. To address this issue, this paper introduces a high-precision target-tracking method with anomaly tracking status detection and recovery. An adaptive feature fusion strategy is proposed to improve the adaptability of the traditional sum of template and pixel-wise learners (Staple) algorithm to changes in target appearance and environmental conditions. Additionally, the Moth Flame Optimization (MFO) algorithm, known for its strong global search capability, is introduced as a re-detection algorithm in case of tracking failure. Furthermore, a trajectory-guided Gaussian initialization technique and an iteration speed update strategy are proposed based on sexual pheromone density to enhance the tracking performance of the introduced re-detection algorithm. Comparative experiments conducted on UAV123 and UAVDT datasets demonstrate the excellent stability and robustness of the proposed algorithm.

Detection Model of Tea Disease Severity under Low Light Intensity Based on YOLOv8 and EnlightenGAN

In response to the challenge of low recognition rates for similar phenotypic symptoms of tea diseases in low-light environments and the difficulty in detecting small lesions, a novel adaptive method for tea disease severity detection is proposed. This method integrates an image enhancement algorithm based on an improved EnlightenGAN network and an enhanced version of YOLO v8. The approach involves first enhancing the EnlightenGAN network through non-paired training on low-light-intensity images of various tea diseases, guiding the generation of high-quality disease images. This step aims to expand the dataset and improve lesion characteristics and texture details in low-light conditions. Subsequently, the YOLO v8 network incorporates ResNet50 as its backbone, integrating channel and spatial attention modules to extract key features from disease feature maps effectively. The introduction of adaptive spatial feature fusion in the Neck part of the YOLOv8 module further enhances detection accuracy, particularly for small disease targets in complex backgrounds. Additionally, the model architecture is optimized by replacing traditional Conv blocks with ODConv blocks and introducing a new ODC2f block to reduce parameters, improve performance, and switch the loss function from CIOU to EIOU for a faster and more accurate recognition of small targets. Experimental results demonstrate that YOLOv8-ASFF achieves a tea disease detection accuracy of 87.47% and a mean average precision (mAP) of 95.26%. These results show a 2.47 percentage point improvement over YOLOv8, and a significant lead of 9.11, 9.55, and 7.08 percentage points over CornerNet, SSD, YOLOv5, and other models, respectively. The ability to swiftly and accurately detect tea diseases can offer robust theoretical support for assessing tea disease severity and managing tea growth. Moreover, its compatibility with edge computing devices and practical application in agriculture further enhance its value.

A transformer-guided cross-modality adaptive feature fusion framework for esophageal gross tumor volume segmentation

Background and ObjectiveAccurate segmentation of esophageal gross tumor volume (GTV) indirectly enhances the efficacy of radiotherapy for patients with esophagus cancer. In this domain, learning-based methods have been employed to fuse cross-modality positron emission tomography (PET) and computed tomography (CT) images, aiming to improve segmentation accuracy. This fusion is essential as it combines functional metabolic information from PET with anatomical information from CT, providing complementary information. While the existing three-dimensional (3D) segmentation method has achieved state-of-the-art (SOTA) performance, it typically relies on pure-convolution architectures, limiting its ability to capture long-range spatial dependencies due to convolution's confinement to a local receptive field. To address this limitation and further enhance esophageal GTV segmentation performance, this work proposes a transformer-guided cross-modality adaptive feature fusion network, referred to as TransAttPSNN, which is based on cross-modality PET/CT scans. MethodsSpecifically, we establish an attention progressive semantically-nested network (AttPSNN) by incorporating the convolutional attention mechanism into the progressive semantically-nested network (PSNN). Subsequently, we devise a plug-and-play transformer-guided cross-modality adaptive feature fusion model, which is inserted between the multi-scale feature counterparts of a two-stream AttPSNN backbone (one for the PET modality flow and another for the CT modality flow), resulting in the proposed TransAttPSNN architecture. ResultsThrough extensive four-fold cross-validation experiments on the clinical PET/CT cohort. The proposed approach acquires a Dice similarity coefficient (DSC) of 0.76 ± 0.13, a Hausdorff distance (HD) of 9.38 ± 8.76 mm, and a Mean surface distance (MSD) of 1.13 ± 0.94 mm, outperforming the SOTA competing methods. The qualitative results show a satisfying consistency with the lesion areas. ConclusionsThe devised transformer-guided cross-modality adaptive feature fusion module integrates the strengths of PET and CT, effectively enhancing the segmentation performance of esophageal GTV. The proposed TransAttPSNN has further advanced the research of esophageal GTV segmentation.

Similar norm more transferable: Rethinking feature norms discrepancy in adversarial domain adaptation

Adversarial learning has become an effective paradigm for learning transferable features in domain adaptation. However, many previous adversarial domain adaptation methods inevitably damage the discriminative information contained in transferable features, which limits the potential of adversarial learning. In this paper, we explore the reason for this phenomenon and find that the model pays more attention to the alignment of feature norms than the learning of domain-invariant features during adversarial adaptation. Moreover, we observe that the feature norms contain some crucial category information, which is ignored in previous studies. To achieve better adversarial adaptation, we propose two novel feature norms alignment strategies: Histogram-guided Norms Alignment (HNA) and Transport-guided Norms Alignment (TNA). Both strategies model the feature norms from the distribution perspective, which not only facilitates the reduction of the norms discrepancy but also makes full use of discriminative information contained in the norms. Extensive experiments demonstrate that progressively aligning the feature norms distributions of two domains can effectively promote the capture of semantically rich shared features and significantly boost the model’s transfer performance. We hope our findings can shed some light on future research of adversarial domain adaptation.

A novel probabilistic approach for driving the sustainable energy circular economy: Innovating efficiency in renewable resource markets

Our research introduces a novel hybrid model aimed at driving the sustainable economy by innovating efficiency in forecasting renewable resource market trends for recovery. The fusion of Hierarchical Recurrent Neural Networks (RNNs) and LeNet-5 Convolutional Neural Networks (CNNs) capitalizes on the distinct advantages of both architectures. RNNs capture temporal dependencies, while CNNs identify spatial patterns, providing a holistic understanding of market dynamics. This symbiosis significantly enhances predictive accuracy, empowering stakeholders with more reliable insights into the trajectory of renewable resource markets. Efficient feature selection is achieved through the incorporation of the Modified Hill Climbing (MHC) algorithm. As an evolutionary feature selection technique, MHC dynamically refines input features during the learning process, adapting to the evolving nature of renewable resource markets. This adaptive feature selection not only improves computational efficiency and interpretability but also ensures a focus on the most relevant information, aligning with the goal of driving sustainable circular economic recovery. The fortified hybrid model, harmonizing RNNs, CNNs, and MHC, showcases heightened robustness and generalization across diverse market conditions. By effectively merging deep learning architectures with an evolutionary feature selection process, the model adeptly captures intricate patterns while mitigating overfitting. This contribution underscores the applicability of the proposed approach to real-world scenarios, positioning it as a catalyst for innovative efficiency in renewable resource markets—a pivotal driver for the recovery of the sustainable economy. Our research marks a crucial advancement in the realm of reliable and adaptable forecasting models, essential for informed decision-making in the dynamic landscape of renewable energy markets.

LDPC-Net: A Lightweight Detail–Content Progressive Coupled Network for Single-Image Dehazing with Adaptive Feature Extraction Block

Image dehazing is an effective means to enhance the quality of images captured in foggy or hazy weather conditions. However, the existing dehazing methods either cannot obtain satisfactory recovery results or have large model parameters. This limits the application of the model on resource-limited platforms. To overcome these limitations, we propose a lightweight yet effective image-dehazing method, named the lightweight detail–content progressive coupled network (LDPC-Net). Within the framework of LDPC-Net, we propose a progressive coupling dehazing paradigm. Specifically, we first estimate the details and content information of the haze-free image, and then fuse these estimations using the progressive coupling method. This proposed dehazing framework markedly enhances the operational efficiency of the model. Meanwhile, considering both the effectiveness and efficiency of the network, we also design a lightweight adaptive feature extraction block serving as the basic feature extraction module of the proposed LDPC-Net. Extensive experimental results demonstrate the effectiveness of our LDPC-Net, outperforming the state-of-the-art methods by boosting the PSNR index over 38.57 dB with only 0.708 M parameters.

An adaptive multi-scale feature fusion and adaptive mixture-of-experts multi-task model for industrial equipment health status assessment and remaining useful life prediction

Health status (HS) assessment and remaining useful life (RUL) prediction are two essential tasks in prognostics and health management. Though HS assessment and RUL prediction based on multi-task learning have achieved considerable progress, the following three challenges still exist. Firstly, it is assumed that these two tasks are related, and the inter-task correlation is ignored. Secondly, it is difficult to extract complex degradation features using the traditional deep network as the shared-bottom structure. Thirdly, inter-task heterogeneity is not considered, which limits the model's generalization ability to different tasks. To overcome these challenges, this work proposes an adaptive multi-scale feature fusion and adaptive mixture-of-experts multi-task model for HS assessment and RUL prediction. By exploiting inter-task affinity to measure the correlation between tasks, it provides guidance for multi-task modeling of industrial equipment. Then, an adaptive multi-scale feature fusion mechanism is designed as the shared-bottom structure to improve the feature extraction ability of the multi-task model. Besides, considering inter-task heterogeneity, an adaptive mixture-of-experts mechanism is developed to adaptively fuse expert features for specific tasks, which enhances the model's adaptability and generalization to different tasks. Finally, experiments on engine degradation data and tool wear data demonstrate that the proposed model outperforms other state-of-the-art baselines.

Active visual continuous seam tracking based on adaptive feature detection and particle filter tracking

Welding seam tracking based on online programming is the future trend of intelligent production. However, most of the existing image processing methods have certain limitations in the adaptability, accuracy, and robustness of weld feature point detection. The online welding method of gas metal arc welding (GMAW) based on active vision sensing is studied in this paper. The Steger sub-pixel detection method is used to guarantee the accuracy of feature point extraction, and a self-adaptive search window and self-adaptive slope extraction are proposed on this basis. The self-adaptive window is generated according to the linear information of the weld area, and the scale factor and range threshold constraint are added to realize the real-time detection of the weld feature information. Screening the center pixel of the laser stripe in the self-adaptive window of the current frame by the initial slope or the self-adaptive slope of the previous frame, the linear information of the weld area is obtained. The self-adaptive slope of the current frame is fitted by the random sampling consistency method, and the pixel margin is retained to adapt to the linear detection of different continuous welds. When arc light and other serious interference make it difficult to obtain weld information, a particle filter is used to make the best prediction of the weld position. Finally, the welding robot platform based on laser vision sensing was built to test various continuous welds of the butt weld, fillet weld, and lap weld. Experimental results show that the detection speed is 27 ms, and the accuracy of detection and tracking can respectively reach 0.03 mm and 0.78 mm, which meets the requirements of weld detection and tracking.

Modal-aware prompt tuning with deep adaptive feature enhancement

Prompt learning has recently emerged as a promising method for fine-tuning vision-language models. By introducing prompts in the text encoder or image encoder, the pre-trained model can quickly adapt to downstream tasks without updating the pre-trained weights. However, prior multi-modal prompt tuning works do not consider the difference in feature distributions between text and images, and adopt the same prompts for both encoders, thus achieving sub-optimal performance in the downstream few-shot learning. In this paper, we propose Modal-Aware Prompt (MAP) to alleviate this issue. Specifically, considering the stability of text features, we design text-specific prompts, which can acquire text class-related information from a general template (i.e., “a photo of a <category>”) by unidirectional attention-based interaction. Additionally, considering the diversity of image features, we design visual-specific prompts to acquire image class-related information and adjust the image features by bidirectional attention-based interaction. To learn hierarchical prompt representations and reinforce the prompt features, we further propose a Deep Adaptive Feature Enhancement (DAFE) module to adaptively utilize the prompt output of the former layer, which can combine instance-level and task-level information simultaneously. Combining the above two designs, our method MAP-DAFE obtains state-of-the-art results on 11 image recognition datasets and has the fastest convergence rate. This proves our MAP-DAFE is effective and efficient.

MFEFNet: A Multi-Scale Feature Information Extraction and Fusion Network for Multi-Scale Object Detection in UAV Aerial Images

Unmanned aerial vehicles (UAVs) are now widely used in many fields. Due to the randomness of UAV flight height and shooting angle, UAV images usually have the following characteristics: many small objects, large changes in object scale, and complex background. Therefore, object detection in UAV aerial images is a very challenging task. To address the challenges posed by these characteristics, this paper proposes a novel UAV image object detection method based on global feature aggregation and context feature extraction named the multi-scale feature information extraction and fusion network (MFEFNet). Specifically, first of all, to extract the feature information of objects more effectively from complex backgrounds, we propose an efficient spatial information extraction (SIEM) module, which combines residual connection to build long-distance feature dependencies and effectively extracts the most useful feature information by building contextual feature relations around objects. Secondly, to improve the feature fusion efficiency and reduce the burden brought by redundant feature fusion networks, we propose a global aggregation progressive feature fusion network (GAFN). This network adopts a three-level adaptive feature fusion method, which can adaptively fuse multi-scale features according to the importance of different feature layers and reduce unnecessary intermediate redundant features by utilizing the adaptive feature fusion module (AFFM). Furthermore, we use the MPDIoU loss function as the bounding-box regression loss function, which not only enhances model robustness to noise but also simplifies the calculation process and improves the final detection efficiency. Finally, the proposed MFEFNet was tested on VisDrone and UAVDT datasets, and the mAP0.5 value increased by 2.7% and 2.2%, respectively.

Deep learning for high-resolution seismic imaging

Seismic imaging techniques play a crucial role in interpreting subsurface geological structures by analyzing the propagation and reflection of seismic waves. However, traditional methods face challenges in achieving high resolution due to theoretical constraints and computational costs. Leveraging recent advancements in deep learning, this study introduces a neural network framework that integrates Transformer and Convolutional Neural Network (CNN) architectures, enhanced through Adaptive Spatial Feature Fusion (ASFF), to achieve high-resolution seismic imaging. Our approach directly maps seismic data to reflection models, eliminating the need for post-processing low-resolution results. Through extensive numerical experiments, we demonstrate the outstanding ability of this method to accurately infer subsurface structures. Evaluation metrics including Root Mean Square Error (RMSE), Correlation Coefficient (CC), and Structural Similarity Index (SSIM) emphasize the model's capacity to faithfully reconstruct subsurface features. Furthermore, noise injection experiments showcase the reliability of this efficient seismic imaging method, further underscoring the potential of deep learning in seismic imaging.

Adaptive Whitening and Feature Gradient Smoothing-Based Anti-Sample Attack Method for Modulated Signals in Frequency-Hopping Communication

Adaptive Whitening and Feature Gradient Smoothing-Based Anti-Sample Attack Method for Modulated Signals in Frequency-Hopping Communication

Morphological and physiological features in small ruminants: an adaptation strategy for survival under changing climatic conditions.

Climate change due to natural human activity is a significant global phenomenon affecting the sustainability of most countries' livestock industries. Climate change factors such as ambient temperature, relative humidity, direct and indirect sun radiation, and wind have significant consequences on feed, water, pasture availability, and the re-emergence of diseases in livestock. All these variables have a considerable impact on livestock production and welfare. However, animals' ability to respond and adapt to changes in climate differs within species and breeds. Comparatively, small ruminants are more adaptive to the adverse effects of climate change than large ruminants in terms of reproduction performance, survival, production yield, and resistance to re-emerging diseases. This is mainly due to their morphological features against harsh climate effects. Tropical breeds are more adaptive to the adverse effects of climate change than small temperate ruminants. However, the difference in morphological characteristics towards adaptation to the impact of climate change will guide the development of suitable policies on the selection of breeding stock suitable for different regions in the world. The choice of breeds based on morphological features and traits is an essential strategy in mitigating and minimizing the effects of climate change on small ruminants' production and welfare. This review highlights the adaptive morphological features within and among breeds of small ruminants toward adaptation to climate change.

AFSDCGN: Adaptive Feature Scaling and Dynamic Contextual Graph Networks for image captioning with unseen relationship detection

AFSDCGN: Adaptive Feature Scaling and Dynamic Contextual Graph Networks for image captioning with unseen relationship detection

Adaptive features of winter triticale accessions from the VIR collection

Background. In the context of global climate change, the study and development of genetic material with environmental plasticity and stability in the manifestation of its traits becomes relevant. The scientific and practical results achieved in triticale breeding place this crop among the most popular cereals in terms of economic importance. However, the main problem for the use of triticale in breeding practice is its limited genetic resources.Materials and methods. The research materials were 161 winter triticale (× Triticosecale Wittm. ex A. Camus) accessions from the global collection of VIR. The study and breeding-oriented assessment of the material were based on conventional breeding techniques and carried out according to the guidelines approved by VIR with minor amendments. The obtained research data underwent statistical analysis using the method by A. V. Kilchevsky and L. V. Khotyleva.Results. Environmental and genetic parameters were analyzed under the conditions of the Middle Volga Region of Russia. Genotypes were identified for their high general adaptability, i. e., securing the highest average yield in the entire set of environments. Cultivars were also selected for their least variable high yields under the impact of weather conditions. The analysis of the studied set of accessions showed that both high-yielding and low-yielding genotypes were stable. The character’s mean value and its environmental sensitivity were relatively independent and could be incorporated in one genotype in various combinations. This finding can be used in the process of triticale breeding.

AAGCN: a graph convolutional neural network with adaptive feature and topology learning

In recent years, there has been a growing prevalence of deep learning in various domains, owing to advancements in information technology and computing power. Graph neural network methods within deep learning have shown remarkable capabilities in processing graph-structured data, such as social networks and traffic networks. As a result, they have garnered significant attention from researchers.However, real-world data often face challenges like data sparsity and missing labels, which can hinder the performance and generalization ability of graph convolutional neural networks. To overcome these challenges, our research aims to effectively extract the hidden features and topological information of graph convolutional neural networks. We propose an innovative model called Adaptive Feature and Topology Graph Convolutional Neural Network (AAGCN). By incorporating an adaptive layer, our model preprocesses the data and integrates the hidden features and topological information with the original data’s features and structure. These fused features are then utilized in the convolutional layer for training, significantly enhancing the expressive power of graph convolutional neural networks.To evaluate the effectiveness of the adaptive layer in the AAGCN model, we conducted node classification experiments on real datasets. The results validate its ability to address data sparsity and improve the classification performance of graph convolutional neural networks.In conclusion, our research primarily focuses on addressing data sparsity and missing labels in graph convolutional neural networks. The proposed AAGCN model, which incorporates an adaptive layer, effectively extracts hidden features and topological information, thereby enhancing the expressive power and classification performance of these networks.

PointAS: an attention based sampling neural network for visual perception.

Harnessing the remarkable ability of the human brain to recognize and process complex data is a significant challenge for researchers, particularly in the domain of point cloud classification-a technology that aims to replicate the neural structure of the brain for spatial recognition. The initial 3D point cloud data often suffers from noise, sparsity, and disorder, making accurate classification a formidable task, especially when extracting local information features. Therefore, in this study, we propose a novel attention-based end-to-end point cloud downsampling classification method, termed as PointAS, which is an experimental algorithm designed to be adaptable to various downstream tasks. PointAS consists of two primary modules: the adaptive sampling module and the attention module. Specifically, the attention module aggregates global features with the input point cloud data, while the adaptive module extracts local features. In the point cloud classification task, our method surpasses existing downsampling methods by a significant margin, allowing for more precise extraction of edge data points to capture overall contour features accurately. The classification accuracy of PointAS consistently exceeds 80% across various sampling ratios, with a remarkable accuracy of 75.37% even at ultra-high sampling ratios. Moreover, our method exhibits robustness in experiments, maintaining classification accuracies of 72.50% or higher under different noise disturbances. Both qualitative and quantitative experiments affirm the efficacy of our approach in the sampling classification task, providing researchers with a more accurate method to identify and classify neurons, synapses, and other structures, thereby promoting a deeper understanding of the nervous system.

Genetic legacy and adaptive signatures: investigating the history, diversity, and selection signatures in Rendena cattle resilient to eighteenth century rinderpest epidemics

BackgroundRendena is a dual-purpose cattle breed, which is primarily found in the Italian Alps and the eastern areas of the Po valley, and recognized for its longevity, fertility, disease resistance and adaptability to steep Alpine pastures. It is categorized as 'vulnerable to extinction' with only 6057 registered animals in 2022, yet no comprehensive analyses of its molecular diversity have been performed to date. The aim of this study was to analyse the origin, genetic diversity, and genomic signatures of selection in Rendena cattle using data from samples collected in 2000 and 2018, and shed light on the breed's evolution and conservation needs.ResultsGenetic analysis revealed that the Rendena breed shares genetic components with various Alpine and Po valley breeds, with a marked genetic proximity to the Original Braunvieh breed, reflecting historical restocking efforts across the region. The breed shows signatures of selection related to both milk and meat production, environmental adaptation and immune response, the latter being possibly the result of multiple rinderpest epidemics that swept across the Alps in the eighteenth century. An analysis of the Rendena cattle population spanning 18 years showed an increase in the mean level of inbreeding over time, which is confirmed by the mean number of runs of homozygosity per individual, which was larger in the 2018 sample.ConclusionsThe Rendena breed, while sharing a common origin with Brown Swiss, has developed distinct traits that enable it to thrive in the Alpine environment and make it highly valued by local farmers. Preserving these adaptive features is essential, not only for maintaining genetic diversity and enhancing the ability of this traditional animal husbandry to adapt to changing environments, but also for guaranteeing the resilience and sustainability of both this livestock system and the livelihoods within the Rendena valley.

Shake it off: exploring drivers and outcomes of autotomy in marine invertebrates.

Autotomy refers to self-amputation where the loss of a limb or organ is generally said to be (1) in response to stressful external stimuli; (2) voluntary and nervously mediated; (3) supported by adaptive features that increase efficiency and simultaneously mediate the cost; and (4) morphologically delineated by a predictable breakage plane. It is estimated that this phenomenon has evolved independently nine different times across the animal kingdom, appearing in many different taxa, including vertebrate and invertebrate as well as aquatic and terrestrial animals. Marine invertebrates use this behaviour in a diversity of manners that have yet to be globally reviewed and critically examined. Here, published data from marine invertebrate taxa were used to explore instances of injury as an evolutionary driver of autotomy. Findings suggest that phyla (e.g. Echinodermata and Arthropoda) possibly experiencing high rates of injury (tissue damage or loss) are more likely to be able to perform autotomy. Additionally, this review looks at various morphological, physiological and environmental conditions that have either driven the evolution or maintained the behaviour of autotomy in marine invertebrates. Finally, the use of autotomic abilities in the development of more sustainable and less ecologically invasive fisheries is explored.