Global Filter Research Articles

A low-complexity parallel local remote microphone technology for multichannel narrowband active noise control systems

Narrowband active noise control (NANC) systems can effectively eliminate periodic disturbances at its error sensors, but sometimes the error sensors are inconvenient to be placed at target locations for a long period. Remote microphone technology (RMT) can tackle this problem by moving quiet zones to the target areas. Nevertheless, the RMT-NANC system has significantly higher computational complexity than conventional NANC systems, particularly for multichannel systems. This hinders their implementation in real-time systems with limited computational resources. The additional computational burden stems from multiple convolutions involving the estimated global high-order secondary paths and observation filters when estimating the virtual error signals. To address this problem, a low-complexity parallel local RMT is proposed based on the narrowband filtered-x least mean square (PLRMT-NFxLMS) algorithm in this paper. Using a two-step local modeling approach, multiple local modeling low-order filters for both secondary paths and observation filters are constructed during the training stage. In the subsequent control stage, virtual error signals are estimated in parallel for different frequency components using these filters instead of global modeling filters, thereby alleviating the substantial computational cost arising from convolutions between lengthy vectors. Moreover, a filtered-error structure, termed the PLRMT-NFeLMS algorithm, is introduced in the proposed algorithm to further reduce the computational complexity. A comprehensive analysis of computational complexity is provided to demonstrate the superiority of the two proposed algorithms. Extensive simulations and real-time experiments were conducted to validate the feasibility and practicability of these proposed methods.

Hierarchical cavitation intensity recognition using Sub-Master Transition Network-based acoustic signals in pipeline systems

Deep learning (DL) has emerged as the most effective approach for cavitation intensity recognition. However, current DL-based models face limitations due to the inherent assumption that all target classes are treated equally. In particular, when certain classes are more difficult to distinguish than others, or when classes can be structured into a hierarchy of categories, DL-based cavitation recognition models struggle to achieve optimal performance. In this study, we propose a hierarchical cavitation intensity recognition framework using the Sub-Master Transition Network (SMTNet) to improve the performance of cavitation intensity recognition of acoustic signal valves. The SMTNet model achieves cavitation intensity recognition from coarse to fine according to the hierarchical properties of cavitation states, overcoming the limitations of DL methods. We also present a global filter layer to address for the long-term dependence of the acoustic signals. In addition, we introduce a 1D double hierarchical residual block to capture sensitive features of acoustic signals. Moreover, a hierarchical multi-label tree is embedded in the SMTNet to map the semantic structure of cavitation states. The proposed model has been evaluated on three real-world cavitation datasets from SAMSON AG, all showing superior results and outperforming SOTA DL methods.

Stereo Matching Method with Cost Volume Collaborative Filtering

Aiming at the problem of matching ambiguity and low disparity accuracy at the object boundary in stereo matching, a novel stereo matching algorithm with cost volume collaborative filtering is proposed. Firstly, for each pixel, two support windows are built, namely a local cross- support window as well as a global support window for the whole image. Secondly, a new adaptive weighted guide filter with a cross-support window as a kernel window is derived, and it is used to locally filter the cost volume. In addition, a minimum spanning tree is constructed in the whole image window, and then the minimum spanning tree filter is used to globally filter the cost volume. The collaborative filtering of cost volume is realized by fusing the filtering results of the local filter and global filter, so that each pixel can not only receive the support of the neighboring pixels in the local adaptive window, but can also receive the effective support of other pixels in the whole image, thus effectively eliminating the matching ambiguity in different texture regions while maintaining the disparity edges. The experimental results show that the average matching error rate of our method on the Middlebury stereo images is 3.17%. Compared with the other state-of-the-art methods, our method has higher robustness and matching accuracy, the generated disparity maps are smoother, and the disparity edges are better preserved.

Event extraction as machine reading comprehension with question-context bridging

Most existing methods regard event extraction as the classification task. They not only heavily rely on named entity recognition, causing error propagation, but are also inefficient in low resource scenarios. To deal with above challenges, we propose an improved machine reading comprehension (MRC) approach, namely MRCBEE. Firstly, a new paradigm is applied to redefine event extraction as MRC task by designing question templates for event detection and argument extraction tasks. Specially, Question-Context Bridging is a new graph structure drawn to reconstruct the semantic relationship between the template and the text, in order to strengthen the prompt role of question templates. Then, a cross-domain attention module is designed to integrate both the semantic feature and global feature of words. A new GNN based on gated mechanism is proposed to capture the global feature and filter the information of invalid neighbors. Finally, the results of our experiments show that MRCBEE achieves better performance than the state-of-the-art methods on ACE2005 and ERE datasets. And it outperforms prior methods in low resource and complex text scenarios.

GRF: A Global Range Filter for LSM-Trees with Shape Encoding

Log-structured merge-trees (LSM-trees) are widely used in key-value stores because of its excellent write performance. To reduce LSM-tree's read amplification due to overlapping sorted runs, each file (i.e., SSTable) in an LSM-tree is typically associated with a point or range filter to reduce unnecessary I/Os to the runs that do not contain the target key (range). However, as modern SSDs get faster, probing multiple in-memory filters per query often makes the system CPU bottlenecked, thus compromising the system's throughput. In this paper, we developed the Global Range Filter (GRF) for RocksDB that reduces the number of filter probes per query to one. We follow the pioneering Chucky's approach by storing the sorted run IDs within the filter. However, we identify two practical challenges in building a global range filter: correctness in multi-version concurrency control and efficiency in frequent updates. We solve both challenges by the novel Shape Encoding algorithm. With further optimizations, GRF achieves a dominating performance over the state-of-the-art filters under different workloads when integrated into RocksDB.

HorSR: High-order spatial interactions and residual global filter for efficient image super-resolution

Recent advances in efficient image super-resolution (EISR) include convolutional neural networks, which exploit distillation and aggregation strategies with copious channel split and concatenation operations to fully exploit limited hierarchical features. In contrast, the Transformer network presents a challenge for EISR because multiheaded self-attention is a computationally demanding process. To respond to this challenge, this paper proposes replacing multiheaded self-attention in the Transformer network with global filtering and recursive gated convolution. This strategy allows us to design a high-order spatial interaction and residual global filter network for efficient image super-resolution (HorSR), which comprises three components: a shallow feature extraction module, a deep feature extraction module, and a high-quality image-reconstruction module. In particular, the deep feature extraction module comprises residual global filtering and recursive gated convolution blocks. The experimental results show that the HorSR network provides state-of-the-art performance with the lowest FLOPs of existing EISR methods.

GSB: GNGS and SAG-BiGRU network for malware dynamic detection.

With the rapid development of the Internet, the continuous increase of malware and its variants have brought greatly challenges for cyber security. Due to the imbalance of the data distribution, the research on malware detection focuses on the accuracy of the whole data sample, while ignoring the detection rate of the minority categories' malware. In the dataset sample, the normal data samples account for the majority, while the attacks' malware accounts for the minority. However, the minority categories' attacks will bring great losses to countries, enterprises, or individuals. For solving the problem, this study proposed the GNGS algorithm to construct a new balance dataset for the model algorithm to pay more attention to the feature learning of the minority attacks' malware to improve the detection rate of attacks' malware. The traditional malware detection method is highly dependent on professional knowledge and static analysis, so we used the Self-Attention with Gate mechanism (SAG) based on the Transformer to carry out feature extraction between the local and global features and filter irrelevant noise information, then extracted the long-distance dependency temporal sequence features by the BiGRU network, and obtained the classification results through the SoftMax classifier. In the study, we used the Alibaba Cloud dataset for malware multi-classification. Compared the GSB deep learning network model with other current studies, the experimental results showed that the Gaussian noise generation strategy (GNGS) could solve the unbalanced distribution of minority categories' malware and the SAG-BiGRU algorithm obtained the accuracy rate of 88.7% on the eight-classification, which has better performance than other existing algorithms, and the GSB model also has a good effect on the NSL-KDD dataset, which showed the GSB model is effective for other network intrusion detection.

Design a multi-objective optimization with dynamic and global filter pruning strategy for convolutional neural network

Design a multi-objective optimization with dynamic and global filter pruning strategy for convolutional neural network

Unraveling biogeographical patterns and environmental drivers of soil fungal diversity at the French national scale

Abstract. The fungal kingdom is among the most diversified kingdoms on Earth, with estimations of up to 12 million species. However, it remains poorly understood, with only 150 000 fungal species currently described. Given the major ecological role of fungi in ecosystem functioning, these numbers stress the importance of investigating fungal diversity description across different ecosystem types. Here, we explored the spatial distribution of the soil fungal diversity on a broad geographical scale, using the French Soil Quality Monitoring Network that covers the whole French territory (2171 soils sampled along a systematic grid). Fungal alpha diversity was assessed directly from soil DNA using a meta-barcoding approach by targeting the 18S rDNA gene. The total accumulated fungal diversity across France included 136 219 operational taxonomic units (OTUs), i.e., about 1 % of worldwide soil fungal diversity (based on a maximum diversity estimate of 12 million) for a territory representing only 0.3 % of the terrestrial surface on Earth. Based on this dataset, the first extensive map of fungal alpha diversity was drawn and showed a heterogeneous and spatially structured distribution in large biogeographical patterns of 231 km radius for richness (Hill diversity of order 0) and smaller patterns of 36 km radius for dominant fungi (Hill diversity of order 2). As related to other environmental parameters, the spatial distribution of fungal diversity (Hill numbers based on different orders of diversity) was mainly influenced by local filters such as soil characteristics and land management and also by global filters such as climate conditions with various relative influences. Interestingly, cropped soils exhibited the highest pool of fungal diversity relative to forest and vineyard soils. To complement this, soil fungal OTU network interactions were calculated for the different land uses across France. They varied hugely and showed a loss of 75 % of the complexity in crop systems and grasslands compared to forests and up to 83 % in vineyard systems. Overall, our study revealed that a nationwide survey with a high spatial-resolution approach is relevant for deeply investigating the spatial distribution and determinism of soil fungal diversity. Our findings provide novel insights for a better understanding of soil fungal ecology across the 18S rDNA gene and upgrade biodiversity conservation policies by supplying representative repositories dedicated to soil fungi.

Global probability distribution structure-sparsity filter pruning for edge fault diagnosis in resource constrained wireless sensor networks

In this paper, a global probability distribution structure-sparsity filter pruning is proposed to address the problem of difficult deployment of diagnostic models in resource constrained wireless sensor networks (WSNs) for edge fault diagnosis. Firstly, local and global weight distributions are analyzed. A global probability distribution weight sparsity method is proposed to obtain the global sparse boundary and the important features of the model. Secondly, according to the distribution of weight amplitude, the problem of uneven weight distribution is disclosed. A computational acceleration sensing method is proposed to reduce the high computational cost caused by small weight amplitude with low importance estimation. Moreover, a novel layer filter clustering pruning scheme is proposed. The intra-layer filters are classified and redundant filters are removed by using the clustering idea according to the predetermined pruning rate. Thus, the structure-sparsity filter pruning is realized. Compared with other advanced filter pruning methods, the proposed method analyzes the global and local model weight distribution and the influence of weight importance on the computational complexity of the model. The proposed method then performs filter pruning on the importance of overall filters for each network layer rather than individual filters. The accuracy of the proposed method on experimental dataset for pruned ResNet8 model under pruning rate at 0.95 is 99.12% with 3.668K parameters and 3.636MFLOPs. The experimental results elucidate that the proposed method is more suitable for deployment in resource-constrained WSNs for fault diagnosis of rotating machinery. This provides a potential solution for practical engineering applications.

FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels

Federated Learning with Noisy Labels (F-LNL) aims at seeking an optimal server model via collaborative distributed learning by aggregating multiple client models trained with local noisy or clean samples. On the basis of a federated learning framework, recent advances primarily adopt label noise filtering to separate clean samples from noisy ones on each client, thereby mitigating the negative impact of label noise. However, these prior methods do not learn noise filters by exploiting knowledge across all clients, leading to sub-optimal and inferior noise filtering performance and thus damaging training stability. In this paper, we present FedDiv to tackle the challenges of F-LNL. Specifically, we propose a global noise filter called Federated Noise Filter for effectively identifying samples with noisy labels on every client, thereby raising stability during local training sessions. Without sacrificing data privacy, this is achieved by modeling the global distribution of label noise across all clients. Then, in an effort to make the global model achieve higher performance, we introduce a Predictive Consistency based Sampler to identify more credible local data for local model training, thus preventing noise memorization and further boosting the training stability. Extensive experiments on CIFAR-10, CIFAR-100, and Clothing1M demonstrate that FedDiv achieves superior performance over state-of-the-art F-LNL methods under different label noise settings for both IID and non-IID data partitions. Source code is publicly available at https://github.com/lijichang/FLNL-FedDiv.

Image denoising using difference classifier and trimmed global mean filter adaptive approach

Image denoising using difference classifier and trimmed global mean filter adaptive approach

GFNet: Global Filter Networks for Visual Recognition.

Recent advances in self-attention and pure multi-layer perceptrons (MLP) models for vision have shown great potential in achieving promising performance with fewer inductive biases. These models are generally based on learning interaction among spatial locations from raw data. The complexity of self-attention and MLP grows quadratically as the image size increases, which makes these models hard to scale up when high-resolution features are required. In this paper, we present the Global Filter Network (GFNet), a conceptually simple yet computationally efficient architecture, that learns long-term spatial dependencies in the frequency domain with log-linear complexity. Our architecture replaces the self-attention layer in vision Transformers with three key operations: a 2D discrete Fourier transform, an element-wise multiplication between frequency-domain features and learnable global filters, and a 2D inverse Fourier transform. Based on this basic design, we develop a series of isotropic models with a Transformer-style simple architecture and CNN-style hierarchical models with better performance. Isotropic GFNet models exhibit favorable accuracy/complexity trade-offs compared to recent vision Transformers and pure MLP models. Hierarchical GFNet models can inherit successful designs in CNNs and be easily scaled up with larger model sizes and more training data, showing strong performance on both image classification (e.g., 85.0% top-1 accuracy on ImageNet-1 k without any extra data or supervision, and 87.4% accuracy with ImageNet-21 k pre-training) and dense prediction tasks (e.g., 54.3 mIoU on ADE20 k val). Our results demonstrate that GFNet can be a very competitive alternative to Transformer-based models and CNNs in terms of efficiency, generalization ability and robustness. Code is available at https://github.com/raoyongming/GFNet.

Lite‐weight semantic segmentation with AG self‐attention

AbstractDue to the large computational and GPUs memory cost of semantic segmentation, some works focus on designing a lite weight model to achieve a good trade‐off between computational cost and accuracy. A common method is to combined CNN and vision transformer. However, these methods ignore the contextual information of multi receptive fields. And existing methods often fail to inject detailed information losses in the downsampling of multi‐scale feature. To fix these issues, we propose AG Self‐Attention, which is Enhanced Atrous Self‐Attention (EASA), and Gate Attention. AG Self‐Attention adds the contextual information of multi receptive fields into the global semantic feature. Specifically, the Enhanced Atrous Self‐Attention uses weight shared atrous convolution with different atrous rates to get the contextual information under the specific different receptive fields. Gate Attention introduces gating mechanism to inject detailed information into the global semantic feature and filter detailed information by producing “fusion” gate and “update” gate. In order to prove our insight. We conduct numerous experiments in common semantic segmentation datasets, consisting of ADE20 K, COCO‐stuff, PASCAL Context, Cityscapes, to show that our method achieves state‐of‐the‐art performance and achieve a good trade‐off between computational cost and accuracy.

Regulation of d-Band Centers in Localized CdS Homojunctions through Facet Control for Improved Photocatalytic Water Splitting.

The accelerated kinetic behaviour of charge carrier transfer and its unhindered surface reaction dynamic process involving oxygenated-intermediate activation and conversion are urgently required in photocatalytic water (H2 O) overall splitting, which has not been nevertheless resolved yet. Herein, localized CdS homojunctions with optimal collocation of high and low index facets to regulate d-band center for chemically adsorbing and activating key intermediates (*-OH and *-O) have been achieved in H2 O overall splitting into hydrogen. Density functional theory, hall effect, and in situ diffuse reflectance infrared Fourier transform spectroscopy confirm that, electrons and holes are kinetically transferred to reductive high index facet (002) and oxidative low index facet (110) of the localized CdS homojunction induced by facet Fermi level difference to dehydrogenate *-OH and couple *-O for hydrogen and oxygen evolution, respectively, along with a solar conversion into hydrogen (STH) of 2.20 % by Air Mass 1.5 Global filter irradiation. These findings contribute to solving the kinetic bottleneck issues of photocatalytic H2 O splitting, which will further enhance STH.

Regulation of d‐Band Centers in Localized CdS Homojunctions through Facet Control for Improved Photocatalytic Water Splitting

AbstractThe accelerated kinetic behaviour of charge carrier transfer and its unhindered surface reaction dynamic process involving oxygenated‐intermediate activation and conversion are urgently required in photocatalytic water (H2O) overall splitting, which has not been nevertheless resolved yet. Herein, localized CdS homojunctions with optimal collocation of high and low index facets to regulate d‐band center for chemically adsorbing and activating key intermediates (*‐OH and *‐O) have been achieved in H2O overall splitting into hydrogen. Density functional theory, hall effect, and in situ diffuse reflectance infrared Fourier transform spectroscopy confirm that, electrons and holes are kinetically transferred to reductive high index facet (002) and oxidative low index facet (110) of the localized CdS homojunction induced by facet Fermi level difference to dehydrogenate *‐OH and couple *‐O for hydrogen and oxygen evolution, respectively, along with a solar conversion into hydrogen (STH) of 2.20 % by Air Mass 1.5 Global filter irradiation. These findings contribute to solving the kinetic bottleneck issues of photocatalytic H2O splitting, which will further enhance STH.

Compressed Gaussian Estimation under Low Precision Numerical Representation.

This paper introduces a novel method for computationally efficient Gaussian estimation of high-dimensional problems such as Simultaneous Localization and Mapping (SLAM) processes and for treating certain Stochastic Partial Differential Equations (SPDEs). The authors have presented the Generalized Compressed Kalman Filter (GCKF) framework to reduce the computational complexity of the filters by partitioning the state vector into local and global and compressing the global state updates. The compressed state update, however, still suffers from high computational costs, making it challenging to implement on embedded processors. We propose a low-precision numerical representation for the global filter, such as 16-bit integer or 32-bit single-precision formats for the global covariance matrix, instead of the expensive double-precision, floating-point representation (64 bits). This truncation can inevitably cause filter instability since the truncated covariance matrix becomes overoptimistic or even turns to be an invalid covariance matrix. We introduce a Minimal Covariance Inflation (MCI) method to make the filter consistent while minimizing the truncation errors. Simulation-based experiments results show significant improvement of the proposed method with a reduction in the processing time with minimal loss of accuracy.

Low-Cost Onboard Multisensor State Estimator Based on Global Mixed Sampling Optimization Filter

Long-term convergent and accurate state estimation( attitude, velocity, and position) is critical to unmanned aerial vehicles (UAVs). However, the measurement accuracy and noise of multiple low-cost sensors onboard are poorer compared to high-precision sensors. To improve the solution accuracy and reliability of UAVs state estimation based on the low-cost sensors, a two-step multi-sensor fusion estimator (federated mixed-sampling Kalman filter, FMSKF) is proposed. Firstly, a multi-sensor integrated navigation model array is designed depending on the different sensors, including the gyroscope, accelerometer, magnetometer, GPS module, and barometer. Then, a three-stage mixed sampling Kalman filter is proposed to obtain the local convergent state vector, which is difficult to meet the flight accuracy requirements. Therefore, a multi-sensor global information optimization filter is proposed to obtain the global convergent navigation solution parameters. Finally, the simulation and flight experimental results and detailed analysis demonstrate that the proposed algorithm can improve the state estimation accuracy, filtering robustness, and obtain desirable navigation performance.

Complex-Valued Convolution and Frequency Global Filter for Automatic Modulation Recognition

Automatic modulation recognition (AMR) plays an important role in cognitive radio and dynamic spectrum access, which has been widely applied in military and civilian applications. Due to the breakthroughs in deep learning (DL), DL-based AMR methods are becoming extremely popular. However, most existing DL-based methods are unable to deal with complex format data, and learning the mappings from the time series or its transformed representation to the true modulation type directly is difficult. To address these difficulties, this letter presents a complex-valued convolution and frequency global filter unit (CGFU), and proposes a hybrid neural network, namely CGF-HNN, which can efficiently exploit features from different domains. We evaluate the recognition performance of the proposed model on two well-known datasets, i.e., RML2016.10a and RML2018.01a. Simulation results show that the proposed model outperforms the existing state-of-the-art models.

"My face, my rules": Enabling Personalized Protection Against Unacceptable Face Editing

Today, face editing is widely used to refine/alter photos in both professional and recreational settings. Yet it is also used to modify (and repost) existing online photos for cyberbullying. Our work considers an important open question: 'How can we support the collaborative use of face editing on social platforms while protecting against unacceptable edits and reposts by others?' This is challenging because, as our user study shows, users vary widely in their definition of what edits are (un)acceptable. Any global filter policy deployed by social platforms is unlikely to address the needs of all users, but hinders social interactions enabled by photo editing. Instead, we argue that face edit protection policies should be implemented by social platforms based on individual user preferences. When posting an original photo online, a user can choose to specify the types of face edits (dis)allowed on the photo. Social platforms use these per-photo edit policies to moderate future photo uploads, i.e., edited photos containing modifications that violate the original photo's policy are either blocked or shelved for user approval. Realizing this personalized protection, however, faces two immediate challenges: (1) how to accurately recognize specific modifications, if any, contained in a photo; and (2) how to associate an edited photo with its original photo (and thus the edit policy). We show that these challenges can be addressed by combining highly efficient hashing based image search and scalable semantic image comparison, and build a prototype protector (Alethia) covering nine edit types. Evaluations using IRB-approved user studies and data-driven experiments (on 839K face photos) show that Alethia accurately recognizes edited photos that violate user policies and induces a feeling of protection to study participants. This demonstrates the initial feasibility of personalized face edit protection. We also discuss current limitations and future directions to push the concept forward.