Context-aware Features Research Articles

AuthorNet: Leveraging attention-based early fusion of transformers for low-resource authorship attribution

Authorship Attribution (AA) is crucial for identifying the author of a given text from a pool of suspects, especially with the widespread use of the internet and electronic devices. However, most AA research has primarily focused on high-resource languages like English, leaving low-resource languages such as Bengali relatively unexplored. Challenges faced in this domain include the absence of benchmark corpora, a lack of context-aware feature extractors, limited availability of tuned hyperparameters, and OOV issues. To address these challenges, this study introduces AuthorNet for authorship attribution using attention-based early fusion of transformer-based language models, i.e., concatenation of an embeddings output of two existing models that were fine-tuned. AuthorNet consists of three key modules: Feature extraction, Fine-tuning and selection of best-performing models, and Attention-based early fusion. To evaluate the performance of AuthorNet, a number of experiments using four benchmark corpora have been conducted. The results demonstrated exceptional accuracy: 98.86 ± 0.01%, 99.49 ± 0.01%, 97.91 ± 0.01%, and 99.87 ± 0.01% for four corpora. Notably, AuthorNet outperformed all foundation models, achieving accuracy improvements ranging from 0.24% to 2.92% across the four corpora.

PTB-DDI: An Accurate and Simple Framework for Drug-Drug Interaction Prediction Based on Pre-Trained Tokenizer and BiLSTM Model.

The simultaneous use of two or more drugs in clinical treatment may raise the risk of a drug-drug interaction (DDI). DDI prediction is very important to avoid adverse drug events in combination therapy. Recently, deep learning methods have been applied successfully to DDI prediction and improved prediction performance. However, there are still some problems with the present models, such as low accuracy due to information loss during molecular representation or incomplete drug feature mining during the training process. Aiming at these problems, this study proposes an accurate and simple framework named PTB-DDI for drug-drug interaction prediction. The PTB-DDI framework consists of four key modules: (1) ChemBerta tokenizer for molecular representation, (2) Bidirectional Long Short-Term Memory (BiLSTM) to capture the bidirectional context-aware features of drugs, (3) Multilayer Perceptron (MLP) for mining the nonlinear relationship of drug features, and (4) interaction predictor to perform an affine transformation and final prediction. In addition, we investigate the effect of dual-mode on parameter-sharing and parameter-independent within the PTB-DDI framework. Furthermore, we conducted comprehensive experiments on the two real-world datasets (i.e., BIOSNAP and DrugBank) to evaluate PTB-DDI framework performance. The results show that our proposed framework has significant improvements over the baselines based on both datasets. Based on the BIOSNAP dataset, the AUC-ROC, PR-AUC, and F1 scores are 0.997, 0.995, and 0.984, respectively. These metrics are 0.896, 0.873, and 0.826 based on the DrugBank dataset. Then, we conduct the case studies on the three newly approved drugs by the Food and Drug Administration (FDA) in 2024 using the PTB-DDI framework in dual modes. The obtained results indicate that our proposed framework has advantages for predicting drug-drug interactions and that the dual modes of the framework complement each other. Furthermore, a free website is developed to enhance accessibility and user experience.

Context-aware feature reconstruction for class-incremental anomaly detection and localization

With the development of deep learning, the unsupervised visual anomaly detection and localization task has gained significant attention in both academia and industry, where only normal data are used for training. Existing methods for this task typically train using all training data simultaneously. However, in practical industrial scenarios, new product classes are usually introduced incrementally, leading to the sequential availability of training data. Such scenarios demand methods for class-incremental anomaly detection and localization (CADL). The main challenge of class-incremental learning is to retain knowledge of old classes when learning new classes. In this article, we aim to effectively leverage limited exemplars of old classes to retain knowledge for the CADL task. Achieving this goal requires a model that can efficiently capture anomaly-identification-related knowledge from limited exemplars. Considering that pixel-level anomaly identification requires an understanding of the surrounding context, we treat context within inputs as valuable anomaly-identification-related knowledge and design a context-aware feature reconstruction (CFR) model to capture such knowledge. Moreover, to avoid inter-class context conflict that may arise with class increments, we design an intermediate feature organization strategy. This strategy and output-level knowledge distillation jointly form dual constraints to regularize the model at both mid-feature and output levels. Utilizing the CFR model with Dual Constraints, the proposed CFRDC can effectively retain old-class knowledge while learning new classes, thus addressing the CADL task. Experimental results on the commonly-used MVTec-AD dataset demonstrate the effectiveness and outstanding performance of the proposed method in CADL.

Revisiting 3D visual grounding with Context-aware Feature Aggregation

3D visual grounding is the task of accurately locating objects in a three-dimensional scene based on textual descriptions. Current approaches mainly depend on downsampling and extracting the point features for fusion with text features. However, the main challenges of these methods are the poor point feature resolution and limited local context during multi-modal fusion, causing visual-linguistic misalignment, particularly for small objects described in the text. The intuitive solution is to get additional object-related point features, gathering more contextual information to augment the representation capability of multimodal features, thereby promoting the representation capabilities of multimodal features. Based on this, we introduce a novel 3D visual grounding framework named Context-aware Feature Aggregation (CFA). The CFA framework includes two key modules: (1) Point Augmented Aggregation Module (PAM), designed to compensate for downsampling-induced information loss by augmenting sampled points with neighboring context for more discriminative features; and (2) Dual Contextual Grouping Attention Module (DCGAM), which iteratively refines features and geometry coordinates from PAM, capturing more global context. We assess the performance of our CFA framework on two point-based datasets: ScanRefer and Nr3D/Sr3D. The CFA framework exhibits efficiency in 3D visual grounding, surpassing the performance of previous methods by experimental results.

CDT-CAD: Context-Aware Deformable Transformers for End-to-End Chest Abnormality Detection on X-Ray Images.

Deep learning methods have achieved great success in medical image analysis domain. However, most of them suffer from slow convergency and high computing cost, which prevents their further widely usage in practical scenarios. Moreover, it has been proved that exploring and embedding context knowledge in deep network can significantly improve accuracy. To emphasize these tips, we present CDT-CAD, i.e., context-aware deformable transformers for end-to-end chest abnormality detection on X-Ray images. CDT-CAD first constructs an iterative context-aware feature extractor, which not only enlarges receptive fields to encode multi-scale context information via dilated context encoding blocks, but also captures unique and scalable feature variation patterns in wavelet frequency domain via frequency pooling blocks. Afterwards, a deformable transformer detector on the extracted context features is built to accurately classify disease categories and locate regions, where a small set of key points are sampled, thus leading the detector to focus on informative feature subspace and accelerate convergence speed. Through comparative experiments on Vinbig Chest and Chest Det 10 Datasets, CDT-CAD demonstrates its effectiveness in recognizing chest abnormities and outperforms 1.4% and 6.0% than the existing methods in AP50 and AR on VinBig dateset, and 0.9% and 2.1% on Chest Det-10 dataset, respectively.

SegCFT: Context-aware Fourier Transform for efficient semantic segmentation

Semantic segmentation has been one of the most critical tasks in computer vision. Recent works mainly focus on improving segmentation performance by designing high-capacity transformer architectures. They try to solve the high data consumption and computing costs required for model training and deployment in the cloud, but the high computation overhead still makes it difficult to be directly applied to limited resource devices. In this paper, we propose a novel fast Fourier Transform (FFT) based Context-aware Feature Mixer under the transformer-like architecture for precise and efficient semantic segmentation, called SegCFT. Different from the self-attention-based transformer, SegCFT uses a Hierarchical Fourier Transform (HFT) to reduce computational cost via non-parametric calculation and promote segmentation performance by fusing the channel-wise and pixel-wise contexts. To integrate the features from the frequency domain of DFT into the spatial domain of the transformer-like architecture, an Adaptive Modulation Unit (AMU) is designed to modulate the frequency-domain features and ensure consistency between the frequency domain and the spatial domain. Experimental evaluation on two semantic segmentation benchmarks, ADE20k and Cityscapes, shows that SegCFT achieves competitive segmentation performance, while the training and inference costs are superior to the previous methods.

Domain-Adaptive and Context-Aware Fall Detection Based on Coarse-Fine Network Learning

Accurate fall detection among older adults is crucial for minimizing injuries and fatalities. However, existing fall detection systems face challenges due to the rarity and variability of falls, compounded by limitations in real-world datasets. To address this, a novel fall detection approach integrating domain adaptation and context-awareness within a Coarse-Fine Network Learning framework is proposed. The model combines high-level semantic understanding with low-level spatial details to achieve robust fall detection across diverse environments. Domain adaptation techniques like transfer learning and domain-specific fine-tuning are introduced to enhance model generalization and adaptability. Additionally, context-aware features, including environmental cues and behavioral patterns, reduce false alarms. Extensive experimentation on real- world datasets demonstrates the superior performance of the model, outperforming traditional approaches. The framework holds promise for deployment in healthcare settings, contributing to improved safety for older adults worldwide. The interpretability of the model's predictions enhances its usability in practical applications.

Dynamic hierarchical intrusion detection task offloading in IoT edge networks

AbstractThe Internet of Things (IoT) has gained widespread importance in recent time. However, the related issues of security and privacy persist in such IoT networks. Owing to device limitations in terms of computational power and storage, standard protection approaches cannot be deployed. In this article, we propose a lightweight distributed intrusion detection system (IDS) framework, called FCAFE‐BNET (Fog based Context Aware Feature Extraction using BranchyNET). The proposed FCAFE‐BNET approach considers versatile network conditions, such as varying bandwidths and data loads, while allocating inference tasks to cloud/edge resources. FCAFE‐BNET is able to adjust to dynamic network conditions. This can be advantageous for applications with particular quality of service requirements, such as video streaming or real‐time communication, ensuring a steady and reliable performance. Early exit deep neural networks (DNNs) have been employed for faster inference generation at the edge. Often, the weights that the model learns in the initial layer may be sufficiently qualified to perform the required classification tasks. Instead of using subsequent layers of DNNs for generating the inference, we have employed the early‐exit mechanism in the DNNs. Such DNNs help to predict a wide range of testing samples through these early‐exit branches, upon crossing a threshold. This method maintains the confidence values corresponding to the inference. Employing this approach, we achieved a faster inference, with significantly high accuracy. Comparative studies exploit manual feature extraction techniques, that can potentially overlook certain valuable patterns, thus degrading classification performance. The proposed framework converts textual/tabular data into 2‐D images, allowing the DNN model to autonomously learns its own features. This conversion scheme facilitated the identification of various intrusion types, ranging from 5 to 14 different categories. FCAFE‐BNET works for both network‐based and host‐based IDS: NIDS and HIDS. Our experiments demonstrate that, in comparison with recent approaches, FCAFE‐BNET achieves a 39.12%–50.23% reduction in the total inference time on benchmark real‐world datasets, such as: NSL‐KDD, UNSW‐NB 15, ToN_IoT, and ADFA_LD.

INDIAN SIGN LANGUAGE RECOGNITION USING CNN WITH SPATIAL PYRAMID AND GLOBAL AVERAGE POOLING

Sign language recognition plays a pivotal role in bridging communication gaps for the speech and hearing-impaired community. In this research, we present an innovative approach to enhance the accuracy and effectiveness of Indian sign language recognition through the integration of convolutional neural networks with spatial pyramid and global average pooling layers. The objective of this study is to address the intricate challenges by exploiting multi-scale feature representations and global context information. This architecture incorporates spatial pyramid layer to capture fine-grained spatial information across multiple scales. Additionally, global average pooling layer is introduced to consolidate context-aware features, further improving the model's discriminative power. Experiments are conducted using a standard dataset, encompassing a diverse range of gestures. The results demonstrate a significant improvement in recognition accuracy compared to conventional models. Incorporating spatial pyramid and global average pooling layers enables our model to effectively recognize the gestures, even in challenging scenarios with variations in lighting, complex background, and signer-dependent factors by achieving high accuracy. This research not only contributes to the advancement of ISL recognition technology but also holds promise for practical applications in real-world communication and assistive technologies.

2.5D UNet with context-aware feature sequence fusion for accurate esophageal tumor semantic segmentation

Segmenting esophageal tumor from computed tomography (CT) sequence images can assist doctors in diagnosing and treating patients with this malignancy. However, accurately extracting esophageal tumor features from CT images often present challenges due to their small area, variable position, and shape, as well as the low contrast with surrounding tissues. This results in not achieving the level of accuracy required for practical applications in current methods. To address this problem, we propose a 2.5D context-aware feature sequence fusion UNet (2.5D CFSF-UNet) model for esophageal tumor segmentation in CT sequence images. Specifically, we embed intra-slice multiscale attention feature fusion (Intra-slice MAFF) in each skip connection of UNet to improve feature learning capabilities, better expressing the differences between anatomical structures within CT sequence images. Additionally, the inter-slice context fusion block (Inter-slice CFB) is utilized in the center bridge of UNet to enhance the depiction of context features between CT slices, thereby preventing the loss of structural information between slices. Experiments are conducted on a dataset of 430 esophageal tumor patients. The results show an 87.13% dice similarity coefficient, a 79.71% intersection over union and a 2.4758 mm Hausdorff distance, which demonstrates that our approach can improve contouring consistency and can be applied to clinical applications.

3D-CAM: a novel context-aware feature extraction framework for neurological disease classification.

In clinical practice and research, the classification and diagnosis of neurological diseases such as Parkinson's Disease (PD) and Multiple System Atrophy (MSA) have long posed a significant challenge. Currently, deep learning, as a cutting-edge technology, has demonstrated immense potential in computer-aided diagnosis of PD and MSA. However, existing methods rely heavily on manually selecting key feature slices and segmenting regions of interest. This not only increases subjectivity and complexity in the classification process but also limits the model's comprehensive analysis of global data features. To address this issue, this paper proposes a novel 3D context-aware modeling framework, named 3D-CAM. It considers 3D contextual information based on an attention mechanism. The framework, utilizing a 2D slicing-based strategy, innovatively integrates a Contextual Information Module and a Location Filtering Module. The Contextual Information Module can be applied to feature maps at any layer, effectively combining features from adjacent slices and utilizing an attention mechanism to focus on crucial features. The Location Filtering Module, on the other hand, is employed in the post-processing phase to filter significant slice segments of classification features. By employing this method in the fully automated classification of PD and MSA, an accuracy of 85.71%, a recall rate of 86.36%, and a precision of 90.48% were achieved. These results not only demonstrates potential for clinical applications, but also provides a novel perspective for medical image diagnosis, thereby offering robust support for accurate diagnosis of neurological diseases.

Cyberbullying Text Identification based on Deep Learning and Transformer-based Language Models

In the contemporary digital age, social media platforms like Facebook, Twitter, and YouTube serve as vital channels for individuals to express ideas and connect with others. Despite fostering increased connectivity, these platforms have inadvertently given rise to negative behaviors, particularly cyberbullying. While extensive research has been conducted on high-resource languages such as English, there is a notable scarcity of resources for low-resource languages like Bengali, Arabic, Tamil, etc., particularly in terms of language modeling. This study addresses this gap by developing a cyberbullying text identification system called BullyFilterNeT tailored for social media texts, considering Bengali as a test case. The intelligent BullyFilterNeT system devised overcomes Out-of-Vocabulary (OOV) challenges associated with non-contextual embeddings and addresses the limitations of context-aware feature representations. To facilitate a comprehensive understanding, three non-contextual embedding models GloVe, FastText, and Word2Vec are developed for feature extraction in Bengali. These embedding models are utilized in the classification models, employing three statistical models (SVM, SGD, Libsvm), and four deep learning models (CNN, VDCNN, LSTM, GRU). Additionally, the study employs six transformer-based language models: mBERT, bELECTRA, IndicBERT, XML-RoBERTa, DistilBERT, and BanglaBERT, respectively to overcome the limitations of earlier models. Remarkably, BanglaBERT-based BullyFilterNeT achieves the highest accuracy of 88.04% in our test set, underscoring its effectiveness in cyberbullying text identification in the Bengali language.

Chest x-ray diagnosis via spatial-channel high-order attention representation learning

Objective. Chest x-ray image representation and learning is an important problem in computer-aided diagnostic area. Existing methods usually adopt CNN or Transformers for feature representation learning and focus on learning effective representations for chest x-ray images. Although good performance can be obtained, however, these works are still limited mainly due to the ignorance of mining the correlations of channels and pay little attention on the local context-aware feature representation of chest x-ray image. Approach. To address these problems, in this paper, we propose a novel spatial-channel high-order attention model (SCHA) for chest x-ray image representation and diagnosis. The proposed network architecture mainly contains three modules, i.e. CEBN, SHAM and CHAM. To be specific, firstly, we introduce a context-enhanced backbone network by employing multi-head self-attention to extract initial features for the input chest x-ray images. Then, we develop a novel SCHA which contains both spatial and channel high-order attention learning branches. For the spatial branch, we develop a novel local biased self-attention mechanism which can capture both local and long-range global dependences of positions to learn rich context-aware representation. For the channel branch, we employ Brownian Distance Covariance to encode the correlation information of channels and regard it as the image representation. Finally, the two learning branches are integrated together for the final multi-label diagnosis classification and prediction. Main results. Experiments on the commonly used datasets including ChestX-ray14 and CheXpert demonstrate that our proposed SCHA approach can obtain better performance when comparing many related approaches. Significance. This study obtains a more discriminative method for chest x-ray classification and provides a technique for computer-aided diagnosis.

A Lightweight Context-Aware Feature Transformer Network for Human Pose Estimation

We propose a Context-aware Feature Transformer Network (CaFTNet), a novel network for human pose estimation. To address the issue of limited modeling of global dependencies in convolutional neural networks, we design the Transformerneck to strengthen the expressive power of features. Transformerneck directly substitutes 3×3 convolution in the bottleneck of HRNet with a Contextual Transformer (CoT) block while reducing the complexity of the network. Specifically, the CoT first produces keys with static contextual information through 3×3 convolution. Then, relying on query and contextualization keys, dynamic contexts are generated through two concatenated 1×1 convolutions. Static and dynamic contexts are eventually fused as an output. Additionally, for multi-scale networks, in order to further refine the features of the fusion output, we propose an Attention Feature Aggregation Module (AFAM). Technically, given an intermediate input, the AFAM successively deduces attention maps along the channel and spatial dimensions. Then, an adaptive refinement module (ARM) is exploited to activate the obtained attention maps. Finally, the input undergoes adaptive feature refinement through multiplication with the activated attention maps. Through the above procedures, our lightweight network provides powerful clues for the detection of keypoints. Experiments are performed on the COCO and MPII datasets. The model achieves a 76.2 AP on the COCO val2017 dataset. Compared to other methods with a CNN as the backbone, CaFTNet has a 72.9% reduced number of parameters. On the MPII dataset, our method uses only 60.7% of the number of parameters, acquiring similar results to other methods with a CNN as the backbone.

TMNet: Triple-modal interaction encoder and multi-scale fusion decoder network for V-D-T salient object detection

Salient object detection methods based on two-modal images have achieved remarkable success with the aid of image acquisition equipment. However, environmental factors often interfere with the Depth and Thermal maps, rendering them ineffective in providing object information. To address this weakness, we utilize the VDT dataset, which includes Visible, Depth, and Thermal images, and propose a triple-modal interaction encoder and multi-scale fusion decoder network (TMNet) to highlight the salient regions. The triple-modal interaction encoder comprises the separation context-aware feature module, channel-wise fusion module, and triple-modal refinement and fusion module, enabling us to fully explore and utilize the complementarity between Visible, Depth, and Thermal information. The multi-scale fusion decoder involves the semantic-aware localizing module and contour-aware refinement module to extract and fuse the location and boundary information, yielding a high-quality saliency map. Extensive experiments on the public VDT-2048 dataset demonstrate that our TMNet outperforms existing state-of-the-art methods in terms of all evaluation metrics.

From Pixel to Patch: Synthesize Context-Aware Features for Zero-Shot Semantic Segmentation.

Zero-shot learning (ZSL) has been actively studied for image classification tasks to relieve the burden of annotating image labels. Interestingly, the semantic segmentation task requires more labor-intensive pixel-wise annotation, but zero-shot semantic segmentation has not attracted extensive research interest. Thus, we focus on zero-shot semantic segmentation that aims to segment unseen objects with only category-level semantic representations provided for unseen categories. In this article, we propose a novel context-aware feature generation network (CaGNet) that can synthesize context-aware pixel-wise visual features for unseen categories based on category-level semantic representations and pixel-wise contextual information. The synthesized features are used to fine-tune the classifier to enable segmenting of unseen objects. Furthermore, we extend pixel-wise feature generation and fine-tuning to patch-wise feature generation and fine-tuning, which additionally considers the interpixel relationship. Experimental results on Pascal-VOC, Pascal-context, and COCO-stuff show that our method significantly outperforms the existing zero-shot semantic segmentation methods.

MSCAF-Net: A General Framework for Camouflaged Object Detection via Learning Multi-Scale Context-Aware Features

The aim of camouflaged object detection (COD) is to find objects that are hidden in their surrounding environment. Due to the factors like low illumination, occlusion, small size and high similarity to the background, COD is recognized to be a very challenging task. In this paper, we propose a general COD framework, termed as MSCAF-Net, focusing on learning multi-scale context-aware features. To achieve this target, we first adopt the improved Pyramid Vision Transformer (PVTv2) model as the backbone to extract global contextual information at multiple scales. An enhanced receptive field (ERF) module is then designed to refine the features at each scale. Further, a cross-scale feature fusion (CSFF) module is introduced to achieve sufficient interaction of multi-scale information, aiming to enrich the scale diversity of extracted features. In addition, inspired the mechanism of the human visual system, a dense interactive decoder (DID) module is devised to output a rough localization map, which is used to modulate the fused features obtained in the CSFF module for more accurate detection. The effectiveness of our MSCAF-Net is validated on four benchmark datasets. The results show that the proposed method significantly outperforms state-of-the-art (SOTA) COD models by a large margin. Besides, we also investigate the potential of our MSCAF-Net on some other vision tasks that are highly related to COD, such as polyp segmentation, COVID-19 lung infection segmentation, transparent object detection and defect detection. Experimental results demonstrate the high versatility of the proposed MSCAF-Net. The source code and results of our method are available at https://github.com/yuliu316316/MSCAF-COD.

CFRLA-Net: A Context-Aware Feature Representation Learning Anchor-Free Network for Pedestrian Detection

High resolution and strong semantic representation are both vital for feature extraction networks of pedestrian detection. The existing high-resolution network (HRNet) has presented a promising performance for pedestrian detection. However, we observed that it still has some significant shortcomings for heavily occluded and small-scale pedestrians. In this paper, we propose to address the shortcomings by extracting semantic and spatial context from HRNet. Specifically, we propose a Context-aware Feature Representation Learning Module (CFRL-Module), which combines a Multi-scale Feature Context Extraction Parallel Block for Convolution and Self-attention (CEPCA-Block) with two parallel paths and an Equivalent FFN (EFFN) Block. The core CEPCA-Block adopts a parallel design to integrate convolution and multi-head self-attention (MHSA) with low parameter computational cost, which can obtain the deep semantic context by convolution path and precise context by MHSA path. Furthermore, to overcome the inefficiency of global MHSA in high-resolution pedestrian detection, we propose a novel local window MHSA, which can significantly reduce memory consumption but barely affect the detection performance. Cascading the proposed CFRL-Module with the anchor-free detection head constitutes our Context-aware Feature Representation Learning Anchor-Free Network (CFRLA-Net). The proposed CFRLA-Net can catch a high-level understanding of the heavily occluded and small-scale pedestrian instances based on HRNet, which can effectively solve the limitation of the insufficient feature extraction ability of HRNet for the hard samples. Experimental results show that CFRLA-Net achieves state-of-the-art performance on CityPersons, Caltech, and CrowdHuman benchmarks.

GPENs: Graph Data Learning With Graph Propagation-Embedding Networks.

Compact representation of graph data is a fundamental problem in pattern recognition and machine learning area. Recently, graph neural networks (GNNs) have been widely studied for graph-structured data representation and learning tasks, such as graph semi-supervised learning, clustering, and low-dimensional embedding. In this article, we present graph propagation-embedding networks (GPENs), a new model for graph-structured data representation and learning problem. GPENs are mainly motivated by 1) revisiting of traditional graph propagation techniques for graph node context-aware feature representation and 2) recent studies on deeply graph embedding and neural network architecture. GPENs integrate both feature propagation on graph and low-dimensional embedding simultaneously into a unified network using a novel propagation-embedding architecture. GPENs have two main advantages. First, GPENs can be well-motivated and explained from feature propagation and deeply learning architecture. Second, the equilibrium representation of the propagation-embedding operation in GPENs has both exact and approximate formulations, both of which have simple closed-form solutions. This guarantees the compactivity and efficiency of GPENs. Third, GPENs can be naturally extended to multiple GPENs (M-GPENs) to address the data with multiple graph structures. Experiments on various semi-supervised learning tasks on several benchmark datasets demonstrate the effectiveness and benefits of the proposed GPENs and M-GPENs.

Global context-aware feature modulation networks for unified multi-scale super-resolution

Global context-aware feature modulation networks for unified multi-scale super-resolution