Deep convolutional neural networks have demonstrated excellent performance in the field of single-image super-resolution (SISR) reconstruction. However, existing methods often suffer from issues such as large number of parameters, intensive computation, and high latency, which limit the application of deep convolutional neural networks on devices with low computational resources. To solve these problems, this paper proposes a lightweight large receptive field network for image super-resolution (LrfSR). The innovations of this paper mainly include the following aspects. Firstly, we design an information distillation module based on large receptive field (LrfDM). The module achieves large receptive field by dilated convolution, and the enlarged receptive field facilitates the network to capture more pixel-to-pixel relationships and fuse multi-scale information in the feature distillation stage. This design effectively extracts the high-frequency features of the image, which can be demonstrated by the feature map. Secondly, a more efficient attention mechanism is introduced into the network, designed as ECCA and SESA, respectively, which achieves an improvement in super-resolution image quality with fewer network parameters. Experiments on Set5, Set14, B100, Urban100 and Manga109 datasets show that the LrfSR model achieves 4-fold super-resolution Peak Signal-to-Noise Ratio (PSNR) values of 32.23 dB, 28.65 dB, 27.59 dB, 26.36 dB and 30.53 dB, which is better than the existing model LKDN etc. Meanwhile, both qualitative and quantitative experimental results show that the LrfSR model explores the potential of large receptive fields in lightweight image super-resolution networks and successfully achieves a balance between high-quality image reconstruction and limited resources. The code and models are available at https://github.com/wanqin557/LrfSR.
Lane line images have the essential attribute of large-scale variation and complex scene information, and the similarity between adjacent lane lines is high, which can easily cause classification errors. And remote lane lines are difficult to recognize due to visual angle changes in width. To address this issue, this paper proposes an effective lane detection framework, which is a hybrid feature fusion network that enhances multiple spatial features and distinguishes key features throughout the entire lane line segment. It enhances and fuses lane line features at multiscale to enhance the feature representation of lane line images, especially at the far end. Firstly, in order to enhance the correlation of multiscale lane features, a multi-head self attention is used to construct a multi-space attention enhancement module for feature enhancement in multispace. Secondly, a spatial separable convolutional branch is designed for the jumping layer structure connecting multiscale lane line features. While retaining feature information of different scales, important lane areas in multiscale feature information are emphasized through the allocation of spatial attention weights. Finally, considering that lane lines are elongated areas in the image, and the background information in the image is much more abundant than lane line information, the flexibility of traditional pooling operations in capturing widely existing anisotropic contexts in actual environments is limited. Therefore, before embedding feature output branches, strip pooling is introduced to refine the representation of lane line information and optimize model performance. The experimental results show that the accuracy on the TuSimple dataset reaches 96.84%, and the F1 score on the CULane dataset reaches 75.9%.
Remote sensing images are essential in various fields, but their high-resolution (HR) acquisition is often limited by factors such as sensor resolution and high costs. To address this challenge, we propose the Multi-image Remote Sensing Super-Resolution with Enhanced Spatio-temporal Feature Interaction Fusion Network ([Formula: see text]N). This model is a deep neural network based on end-to-end. The main innovations of the [Formula: see text]N network model include the following aspects. Firstly, through the Attention-Based Feature Encoder (ABFE) module, the spatial features of low-resolution (LR) images are precisely extracted. Combined with the Channel Attention Block (CAB) module, global information guidance and weighting are provided for the input features, effectively strengthening the spatial feature extraction capability of ABFE. Secondly, in terms of temporal feature modeling, we designed the Residual Temporal Attention Block (RTAB). This module effectively weights k LR images of the same location captured at different times via a global residual temporal connection mechanism, fully exploiting their similarities and temporal dependencies, and enhancing the cross-layer information transmission. The ConvGRU-RTAB Fusion Module (CRFM) captures the temporal features using RTAB based on ABFE and fuses the spatial and temporal features. Finally, the Decoder module enlarges the resolution of the fused features to achieve high quality super resolution image reconstruction. The comparative experiment results show that our model achieves notable improvements in the cPSNR metric, with values of 49.69 dB and 51.57 dB in the NIR and RED bands of the PROBA-V dataset, respectively. The visual quality of the reconstructed images surpasses that of state-of-the-art methods, including TR-MISR and MAST etc.
Chinese possesses the essential attributes of unique character composition structure and the nested nature of medical entities, which causes many challenges for Chinese Electronic Health Records (EHRs) in medical named entity recognition tasks, such as scarce annotated data, strong tokenization ambiguity, and blurred entity boundaries. This increases the difficulty of extracting medical named entity categories. The paper proposes an effective Chinese clinical named entity recognition model that integrates BERT and adversarial enhancement in a dual channel architecture to address this issue. Firstly, the model integrates various advanced technologies, such as Bidirectional Long Short-Term Memory networks (BiLSTM), Iterative Deep Convolutional Neural Networks (IDCNN), and Conditional Random Fields (CRF), to improve the accuracy of named entity recognition. Secondly, the paper collected texts from medical record websites and utilized the YEDDA tool for professional annotation and processing of these texts, ultimately forming a more comprehensive target dataset. This process ensures that the model is exposed to representative Chinese clinical data during training, thereby improving recognition performance.Finally, experimental results indicate that the BPBIC model achieved a precision of 93.80%, a recall of 94.44%, and an F1 score of 94.12% on the augmented dataset CCKS2019 (CCKS2019+). Moreover, through knowledge graph analysis of medical entities extracted from single and multiple disease EHRs, the model assists doctors in achieving rapid and accurate diagnoses, thereby enhancing the efficiency of healthcare professionals.
2 July 2025 in Journal of Visual Communication and Image Representation