High-level Information Research Articles

Object detection with a dynamic interactive network based on relational graph routing

Combinatorial relational reasoning in neural networks used for object detection is usually static; therefore, it cannot selectively fuse visual information and semantic relations, which limits their performance. To address this problem, we propose a relational graph routing network (RGRN) that enables the dynamic interaction of visual and semantic features. The network consists of a dynamic graph network, dual path-sharing module, and relational routing interaction module. First, we used a data-driven technique to obtain the semantic information between tags from the dataset. Rich semantic information was obtained by calculating the similarity between tags. Second, the two types of semantic information were fused using a dynamic graph network to capture high-level semantic information. The visual and semantic features are then filtered and encoded through the dual path-sharing module to obtain enhanced visual and semantic features. Finally, three units were used to dynamically fuse visual and semantic information in the relational routing interaction module, which densely links the three units and routers to construct a routing space that can autonomously decide on the optimal fusion path through model learning. A series of experiments was conducted on the MS COCO dataset. RGRN achieved 54.7% box AP on object detection, which was 2.8% box AP higher than that of the Cascade Mask R-CNN. The experimental results show that the routing space enables better interaction between visual and semantic information. Therefore, our method can achieve better performance than many state-of-the-art methods.

Full-color biomass carbon dots for high-level information encryption and multi-color light emitting diode applications.

Six biomass carbon dots (BCDs) with adjustable emission from 450 to 680nm under a single wavelength excitation were successfully synthesized from spinach via solvent control strategy. The obtained BCDs show blue, green, yellow, violet, pink, and red emission with high photoluminescence quantum yield (PLQY = 12.68 ~ 30.77%). Detailed characterizations disclose that the tunable-emission mechanism is caused by the synergistic effect of carbon conjugate and surface oxidation degree. Meanwhile, full-color photoluminescence BCDs/PVP powder and BCDs/PVP/PVA films were fabricated by utilizing the prepared BCDs combined with polyvinylpyrrolidone (PVP) and polyvinyl alcohol (PVA), respectively, which presented excellent high-level information encryption application. Importantly, multi-color and white light-emitting diode (LED) with Commission Internationale de L' Eclairage (CIE) of blue (0.25, 0.29); green (0.25, 0.31); yellow (0.42, 0.45); red (0.52, 0.31); and white (0.32, 0.31) were achieved by only using our prepared BCDs. This work provides a valuable strategy of preparing multi-color BCDs using readily available biomass materials and paves a way for high-level information encryption and LED applications.

A local enhanced mamba network for hyperspectral image classification

Deep learning has significantly advanced hyperspectral image (HSI) classification, primarily due to its robust nonlinear feature extraction capabilities. The vision transformer has achieved notable performance but is limited by the quadratic computational burden of its self-attention mechanism. Recently, a network based on state space model named Mamba, has attracted considerable attention for its linear complexity and commendable performance. Nevertheless, Mamba was originally designed for one-dimensional causal sequence modeling, and its effectiveness in inherent non-causal HSI classification remains to be fully validated. To address this issue, we propose a novel Local Enhanced Mamba (LE-Mamba) network for hyperspectral image classification, which mainly comprises a Local Enhanced Spatial SSM (LES-S6), a Central Region Spectral SSM (CRS-S6), and a Multi-Scale Convolutional Gated Unit (MSCGU). The LES-S6 improves non-causal local feature extraction by incorporating a multi-directional local spatial scanning mechanism. Additionally, the CRS-S6 employs a bidirectional scanning mechanism in the spectral dimension to capture fine spectral details and integrate them with spatial information. The MSCGU utilizes a convolutional gating mechanism to aggregate features from diverse scanning routes and extract high-level semantic information. The overall accuracies of LE-Mamba on Indian Pines, WHU-Hi-HanChuan, WHU-Hi-LongKou, and Pavia University datasets are 99.16 %, 98.16 %, 99.57 %, and 99.63 %, respectively. Extensive experimental results on these four public datasets demonstrate that the LE-Mamba outperforms eight mainstream deep learning models in classification performance.

CPOpt: A modular framework for genetic algorithm optimization and post-optimization analysis in complex charged particle optical design

This article reports on the development of an optimization framework for charged particle optics design (CPOpt). The optimization part of CPOpt involves a custom-developed Python multi-objective genetic algorithm (MOGA), which incorporates NSGA-II to optimize for multiple objectives, such as particle transmission and beam spot size. The simultaneous tuning of different types of parameters, such as electrode voltages and geometrical parameters, is facilitated by creating isolated groups of parameters. Modeling of parameter configurations is done with the charged particle optics simulation tool SIMION and a ZeroMQ-based communication interface enables a fully automated interaction with the MOGA. The post-optimization analysis part of CPOpt provides standardized and broadly applicable methods to identify suitable solutions, based on the outcome of the optimization part. Global sensitivity analysis, based on the Delta Moment-Independent-Measure in combination with dedicated Latin hypercube sampling, allows higher-level information about parameter sensitivity and robustness to be extracted, as well as effective randomized local optimization. Demonstrated on a two-lens system with intermediate aperture, the CPOpt framework effectively optimized the two conflicting objectives of reduced beam spot size and increased transmission at the detector plane for 12 parameters, covering both electrode voltages and geometrical parameters. The optimization process was performed within less than 11h on a workstation, while all the simulations required for the post-optimization analysis took another 7h. The additional computational effort for the post-optimization analysis can contribute to deliver solutions with high performance and stability.

Rapid Learning of Temporal Dependencies at Multiple Timescales.

Our environment contains temporal information unfolding simultaneously at multiple timescales. How do we learn and represent these dynamic and overlapping information streams? We investigated these processes in a statistical learning paradigm with simultaneous short and long timescale contingencies. Human participants (n = 96) played a game where they learned to quickly click on a target image when it appeared in one of nine locations, in eight different contexts. Across contexts, we manipulated the order of target locations: at a short timescale, the order of pairs of sequential locations in which the target appeared; at a longer timescale, the set of locations that appeared in the first versus the second half of the game. Participants periodically predicted the upcoming target location, and later performed similarity judgments comparing the games based on their order properties. Participants showed context-dependent sensitivity to order information at both short and long timescales, with evidence of stronger learning for short timescales. We modeled the learning paradigm using a gated recurrent network trained to make immediate predictions, which demonstrated multilevel learning timecourses and patterns of sensitivity to the similarity structure of the games that mirrored human participants. The model grouped games with matching rule structure and dissociated games based on low-level order information more so than high-level order information. The work shows how humans and models can rapidly and concurrently acquire order information at different timescales.

Do the best of all together: Hierarchical spatial-frequency fusion transformers for animal re-identification

Animal re-identification is fundamental in the ecology and ethology community for understanding the Earth’s ecosystems. Due to the uncertainty of photographing animals in the wild, such as the position and angle of capture and the variations in animal individuals as well as in their poses and habitats, building image-based visual models for re-identifying animal individuals is a challenging task. We propose a novel framework, hierarchical spatial-frequency fusion transformers, to address animal re-identification. We first use spatial and frequency representation learning to capture effective deep features and then employ hierarchical transformer-based representation learning to consolidate low-level detailed information into high-level semantic information from a global perspective. Through this process, we construct a deeply supervised nonlinear aggregation method to enhance finer multi-scale, multi-level and cross-domain features. Our method illustrates the case of “do the best of all together”, meaning that only when both the frequency and spatial domains are combined can we achieve the best performance. The experimental results demonstrate that our approach achieves significantly higher performance than other state-of-the-art methods.

Visible thermal person re-identification via multi-branch modality residual complementary learning

Visible-thermal Person Re-identification (VT Re-ID) is a challenging task in all-weather surveillance system. Existing methods concentrate on extracting the modality-shared features, ignoring the discriminative inter-modality complementary features. To tackle this issue, we propose a multi-branch modality residual complementary learning method which consists of the modality residual complementary learning (MRCL) module and the multi-branch feature learning (MBFL) module. The MRCL module can be easily integrated into existing CNN baselines and drive the network to focus on both intra-modality and inter-modality information. On one hand, we adopt the basic two-stream network to obtain the intra-modality features, on the other hand, we capture the inter-modality complementary features within the residual image obtained by cross-modality correlation saliency erasing operation. To handle the intra-modality variations, we employ the MBFL module to capture local spatial features and local channel features, then integrate them with global features to achieve part-to-part and high-level semantic information matching. Finally, the discriminability and robustness of the ultimate representations are enhanced by multi-branch constraint loss learning. Extensive experiments on RegDB and SYSU-MM01 datasets demonstrate the superiority of our proposed method compared with state-of-the-art methods.

Pest-ConFormer: A hybrid CNN-Transformer architecture for large-scale multi-class crop pest recognition

Crop pests are acknowledged as the major factors in reducing the yield and quality of agricultural production worldwide. It is an urgent necessity to recognize crop pests accurately to protect the crop in the early stage to reduce the loss for the agricultural economy. Due to the ecological characteristics of the crop pests and the complex background in fields, the crop pests show high inter-class similarity and significant intra-class variation in external morphology appearance, which makes current recognition methods suffer from low classification accuracy and poor generalization ability in complex natural environment recognition tasks. To tackle this problem, a hybrid convolutional neural network and transformer-based model, namely Pest-ConFormer, featured with multi-scale weakly supervised feature selection mechanisms is proposed, which has shown excellent multi-scale discriminative feature extraction in fine-grained visual classification (FGVC) tasks. This method employs a hybrid convolution-transformer encoder architecture pre-training in a self-supervised masked autoencoder manner as a backbone to learn pests’ highly discriminative features across various scales. Next, a dual-path feature aggregation structure with a top-down FPN-like feature pathway and a bottom-up PANet-like feature pathway based on attention mechanisms is designed to learn high-level global context information and low-level local detailed feature representation. Thirdly, a fine-grained classification module using weakly supervised learning is introduced to select the discriminative feature points in different pyramidal levels. Then, these feature points are fed into a graph convolutional network to accomplish classification. Several experiments are conducted on the large-scale multi-class IP102 benchmark dataset, and the proposed method achieves an accuracy of 77.81 % regarding crop pest recognition. The experimental results indicate that our approach outperforms other state-of-the-art methods by nearly 2 percent points, demonstrating that the proposed hybrid architecture with dual-path feature aggregation and fine-grained classification modules can be more effective in the crop pest recognition field than CNN-based methods and can be deployed in the practical natural environment. The source code will be available at https://github.com/mwfang/pestconformer.

Three-stage polyp segmentation network based on reverse attention feature purification with Pyramid Vision Transformer

Colorectal polyps serve as potential precursors of colorectal cancer and automating polyp segmentation aids physicians in accurately identifying potential polyp regions, thereby reducing misdiagnoses and missed diagnoses. However, existing models often fall short in accurately segmenting polyps due to the high degree of similarity between polyp regions and surrounding tissue in terms of color, texture, and shape. To address this challenge, this study proposes a novel three-stage polyp segmentation network, named Reverse Attention Feature Purification with Pyramid Vision Transformer (RAFPNet), which adopts an iterative feedback UNet architecture to refine polyp saliency maps for precise segmentation. Initially, a Multi-Scale Feature Aggregation (MSFA) module is introduced to generate preliminary polyp saliency maps. Subsequently, a Reverse Attention Feature Purification (RAFP) module is devised to effectively suppress low-level surrounding tissue features while enhancing high-level semantic polyp information based on the preliminary saliency maps. Finally, the UNet architecture is leveraged to further refine the feature maps in a coarse-to-fine approach. Extensive experiments conducted on five widely used polyp segmentation datasets and three video polyp segmentation datasets demonstrate the superior performance of RAFPNet over state-of-the-art models across multiple evaluation metrics.

What Encourages Patients to Recommend Their Doctor After an Online Medical Consultation? The Influence of Patient-Centered Communication, Trust, and Negative Health Information Seeking Experiences

ABSTRACT The doctor-patient relationship in China has become increasingly tense, with patients lacking trust in doctors. Meanwhile, online healthcare flourished, accelerated by the COVID-19 pandemic. This study utilized the direct and indirect pathway model of clinician-patient communication to health outcomes and online trust theory to examine the associations between online patient-centered communication (OPCC), benevolence and ability trust in doctors, negative online health information seeking experiences, and willingness to recommend doctors. The findings revealed that benevolence and ability trust mediated the relationship between OPCC and willingness to recommend doctors. Additionally, when participants had a high level of negative online health information seeking experiences, OPCC had a stronger effect on ability trust; meanwhile, the mediation effect of ability trust between the relationship of OPCC and willingness to recommend was stronger. This study also discussed theoretical and practical implications.

REDef-DETR: real-time and efficient DETR for industrial surface defect detection

Abstract Industrial surface defect detection is an important part of industrial production, which aims to identify and detecting various defects on the surface of product to ensure quality and meet customer requirements. With the development of deep learning and image processing technologies, the surface defect detection methods based on computer vision has become the mainstream method. However, the prevalent convolutional neural network-based defect detection methods also have many problems. For example, these methods rely on post-processing of Non-Maximum Suppression and have poor detection ability for small targets, which affects the speed and accuracy of surface defect detection in industrial scenarios. Therefore, we propose a novel DEtection TRansformer-based surface defect detection method. Firstly, we propose a Multi-scale Contextual Information Dilated module and fuse it into the backbone. The module is mainly composed of large kernel convolutions, which aims to expand the receptive field of the model, thus reducing the leakage rate of the model. Moreover, we design an efficient encoder which mainly contains two important modules, namely feature enhancement based on cascaded group attention module and efficient feature fusion module based on content-aware. The former module effectively enhances the high-level semantic information extracted by the backbone, thus enabling the model to better interpret features, and it can improve the problem of high computational cost of transformer encoder, thus increasing the detection speed. The latter module performs multi-scale feature fusion across the feature information of various scales, thus improving the detection accuracy of the model for small-size defects. Experimental results show that the proposed method achieves 80.6%mAP and 80.3FPS on NEU-DET, and 98.0%mAP and 79.4FPS on PCB-DET. Our proposed method exhibits excellent detection performance and achieves real-time and efficient surface defect detection capability to meet the needs of industrial surface defect detection.

Cascaded Aggregation Convolution Network for Salient Grain Pests Detection.

Pest infestation poses significant threats to grain storage due to pests' behaviors of feeding, respiration, excretion, and reproduction. Efficient pest detection and control are essential to mitigate these risks. However, accurate detection of small grain pests remains challenging due to their small size, high variability, low contrast, and cluttered background. Salient pest detection focuses on the visual features that stand out, improving the accuracy of pest identification in complex environments. Drawing inspiration from the rapid pest recognition abilities of humans and birds, we propose a novel Cascaded Aggregation Convolution Network (CACNet) for pest detection and control in stored grain. Our approach aims to improve detection accuracy by employing a reverse cascade feature aggregation network that imitates the visual attention mechanism in humans when observing and focusing on objects of interest. The CACNet uses VGG16 as the backbone network and incorporates two key operations, namely feature enhancement and feature aggregation. These operations merge the high-level semantic information and low-level positional information of salient objects, enabling accurate segmentation of small-scale grain pests. We have curated the GrainPest dataset, comprising 500 images showcasing zero to five or more pests in grains. Leveraging this dataset and the MSRA-B dataset, we validated our method's efficacy, achieving a structure S-measure of 91.9%, and 90.9%, and a weighted F-measure of 76.4%, and 91.0%, respectively. Our approach significantly surpasses the traditional saliency detection methods and other state-of-the-art salient object detection models based on deep learning. This technology shows great potential for pest detection and assessing the severity of pest infestation based on pest density in grain storage facilities. It also holds promise for the prevention and control of pests in agriculture and forestry.

MACCoM: A multiple attention and convolutional cross-mixer framework for detailed 2D biomedical image segmentation

The UNet architecture, which is widely used for biomedical image segmentation, has limitations like blurred feature maps and over- or under-segmented regions. To overcome these limitations, we propose a novel network architecture called MACCoM (Multiple Attention and Convolutional Cross-Mixer) – an end-to-end depthwise encoder-decoder fully convolutional network designed for binary and multi-class biomedical image segmentation built upon deeperUNet. We proposed a multi-scope attention module (MSAM) that allows the model to attend to diverse scale features, preserving fine details and high-level semantic information thus useful at the encoder-decoder connection. As the depth increases, our proposed spatial multi-head attention (SMA) is added to facilitate inter-layer communication and information exchange, enabling the network to effectively capture long-range dependencies and global context. MACCoM is also equipped with a convolutional cross-mixer we proposed to enhance the feature extraction capability of the model. By incorporating these modules, we effectively combine semantically similar features and reduce artifacts during the early stages of training. Experimental results on 4 biomedical datasets crafted from 3 datasets of varying modalities consistently demonstrate that MACCoM outperforms or matches state-of-the-art baselines in the segmentation tasks. With Breast Ultrasound Image (BUSI), MACCoM recorded 99.06 % Jaccard, 77.58 % Dice, and 93.92 % Accuracy, while recording 99.50 %, 98.44 %, and 99.29 % respectively for Jaccard, Dice, and Accuracy on the Chest X-ray (CXR) images used. The Jaccard, Dice, and Accuracy for the High-Resolution Fundus (HRF) images are 95.77 %, 74.35 %, and 95.95 % respectively. The findings here highlight MACCoM's effectiveness in improving segmentation performance and its valuable potential in image analysis.

DIAGNOSTICS OF POSTURAL DISORDERS IN CHILDREN USING COMPUTER PHOTOMETRY

Actuality of the research. Literary and statistical data show that the level of morbidity among children in Ukraine remains high. Important to note that musculoskeletal system and connective tissue diseases take the fifth place among the morbidity structure, while the postural disorders and scoliosis remain the most urgent problem in school­age children. The aim of study is to check the computer photometry method efficiency for postural disorders diagnostics in school­age children with different levels of motor activity. Research methodology. In order to improve the dynamic control over the posture state, to increase the study objectification, to reduce the examination time and simplify the statistical material processing, a software complex for diagnosing posture disorders using the computer photometry method was used. Results. It was found that 25% of examined school­age children had postural disorders. Most often, postural disorders were observed within the age of 10­13 years, while in girls, postural disorders were registered 10% more often than in boys. Systematic exercise does not automatically guarantee the correct posture formation. In children­athletes, more pronounced indicators of angular anthropometric parameters asymmetry were registered, as a result of asymmetric back muscles load distribution. Children who did not exercise were more prone to kyphotic posture developing. Conclusions. As instrumental diagnostics, the computer photometry method has high level of informativeness and reliability, helps to maximize the data objectification and is effective in postural disorders detecting during as screening and as mass examinations.

Multiview ensemble clustering of hypergraph p-Laplacian regularization with weighting and denoising

Multiview clustering has gained attention for its ability to incorporate complementary information from multiple sources of data, leading to better clustering results. However, these methods don't sufficiently mine high-dimensional information of non-linear subspace or ignore important high-level information between basic partitions (BPs), which are obtained via single-view clustering that could help to overcome differences between heterogeneous feature spaces and defined in Eq. (4). Additionally, existing multiview ensemble clustering methods neglect the noise arising from the generation phase. In light of this, we first propose a novel multiview subspace clustering method with hypergraph p-Laplacian regularization and denoising. Specifically, to utilize the high-dimensional information, a hypergraph p-Laplacian regularized term is added to the model along with low-rank subspace learning to capture the different hierarchical structures in the data. A denoising algorithm based on KMeans and K-nearest neighbor is used to minimize the noise of similarity matrix. Then utilizing this approach as a backbone, a multiview ensemble clustering of hypergraph p-Laplacian regularization with weighting and denoising method is proposed. A hybrid strategy and a novel global weighting ensemble strategy is further proposed to extract high-level information across all the BPs. By integrating hypergraph p-Laplacian operator, low-rank subspace learning, denoising, and weighting ensemble strategy in a unified framework, this ensemble approach adequately learns latent structures and complementary information. Experimental results on multiple datasets demonstrate the efficacy of this approach.

Feature aggregation network for small object detection

Due to the miniature scale and limited identifiable features, small objects pose a significant challenge in detection. Improving the accuracy of small object detection is a momentous issue of concern among researchers. Feature pyramid network employs a divide-and-conquer strategy for detecting small objects in low-level networks. However, the limited semantic information in these networks results in suboptimal performance in small object detection. To address this issue, we fully utilize information from all feature levels and propose a Feature Aggregation Network (FAN). We investigate information propagation pathways in neural networks, analyze early fusion and late fusion of features, and introduce a dual top-down pathway that utilizes high-level semantic information to consistently reinforce low-level spatial information. We design a Feature-Aware Module that narrows the semantic gap and steers the network toward learning features that favor small object detection. We employ deformable convolution to accurately locate the boundaries of objects with varying shapes and sizes. FAN can function as a plug-and-play component with minimal computational overhead and be trained end-to-end alongside backbone networks. Extensive experiments are conducted on the COCOs, TinyPerson, and VisDrone datasets. The highly competitive results demonstrate that our approach exhibits robust generalization capabilities and can further improve the accuracy of small object detection.

DBHF: A double fusion backbone and bidirectional feature hybrid fusion detector for high-precision inspection of avionics solder joint defects

The quality of avionics thermistor wire solder joints has a critical impact on the performance of in-orbit spacecraft. However, it is still hard to simultaneously realize a high-precision inspection of the multi-scale internal and external defects of avionics solder joints. Herein, in combination with active infrared thermography technique, an innovative DBHF detector with a double fusion backbone and a learnable weighted multi-scale bidirectional feature hybrid fusion pyramid network (BdFPN) is demonstrated based on RT-DETR framework. Specifically, the double fusion backbone framework comprises with two lightweight convolutional neural network-based backbones. Compared with conventional single backbone, the double-backbone design forms a multi-level Resnet-like structure, helping to enrich the extracted multi-dimension feature information and retain rich detail information of small-scale defects. The complex learnable weighted multi-scale BdFPN is designed for cross fusion of deep features. One or more additional multi-scale inputs are added to each node involved in feature fusion to aggregate more features from multiple scales and strengthen the interaction between low-level details and high-level semantic information, enabling the detector to make full use of multi-level feature information. Meanwhile, a learnable weight coefficient is set on each node involved in feature fusion and the importance of the input to each node is estimated by training, so that the effective information can be deeply aggregated at different levels. Our DBHF detector achieves a 92.7 % mAP@0.5 on a self-made avionics solder joint dataset with a body size of only 27.2 MB and FPS of 149, outperforming all the typical advanced real-time detectors.

The Complex Role Played by the Default Mode Network during Sexual Stimulation: A Cluster-Based fMRI Meta-Analysis.

The default mode network (DMN) is a complex network that plays a significant and active role during naturalistic stimulation. Previous studies that have used naturalistic stimuli, such as real-life stories or silent or sonorous films, have found that the information processing involved a complex hierarchical set of brain regions, including the DMN nodes. The DMN is not involved in low-level features and is only associated with high-level content-related incoming information. The human sexual experience involves a complex set of processes related to both external context and inner processes. Since the DMN plays an active role in the integration of naturalistic stimuli and aesthetic perception with beliefs, thoughts, and episodic autobiographical memories, we aimed at quantifying the involvement of the nodes of the DMN during visual sexual stimulation. After a systematic search in the principal electronic databases, we selected 83 fMRI studies, and an ALE meta-analysis was calculated. We performed conjunction analyses to assess differences in the DMN related to stimulus modalities, sex differences, and sexual orientation. The results show that sexual stimulation alters the topography of the DMN and highlights the DMN's active role in the integration of sexual stimuli with sexual schemas and beliefs.

Radiomics-Guided Deep Learning Networks Classify Differential Diagnosis of Parkinsonism.

The differential diagnosis between atypical Parkinsonian syndromes may be challenging and critical. We aimed to proposed a radiomics-guided deep learning (DL) model to discover interpretable DL features and further verify the proposed model through the differential diagnosis of Parkinsonian syndromes. We recruited 1495 subjects for 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) scanning, including 220 healthy controls and 1275 patients diagnosed with idiopathic Parkinson's disease (IPD), multiple system atrophy (MSA), or progressive supranuclear palsy (PSP). Baseline radiomics and two DL models were developed and tested for the Parkinsonian diagnosis. The DL latent features were extracted from the last layer and subsequently guided by radiomics. The radiomics-guided DL model outperformed the baseline radiomics approach, suggesting the effectiveness of the DL approach. DenseNet showed the best diagnosis ability (sensitivity: 95.7%, 90.1%, and 91.2% for IPD, MSA, and PSP, respectively) using retained DL features in the test dataset. The retained DL latent features were significantly associated with radiomics features and could be interpreted through biological explanations of handcrafted radiomics features. The radiomics-guided DL model offers interpretable high-level abstract information for differential diagnosis of Parkinsonian disorders and holds considerable promise for personalized disease monitoring.

Blind image quality index with high-level Semantic Guidance and low-level fine-grained Representation

Image Quality Assessment (IQA) has received unprecedented attention due to the extensive applications in benchmarking image processing algorithms and systems. Despite great progress in IQA, most previous frameworks either utilized only high-level semantic features or simply stacked multi-level features to account for the distortions, resulting in limited performance. The initial visual perception is formed after that the information is processed by the primary visual cortex and the advanced visual cortex. However, the information transmission of the cerebral cortex is not unidirectional, that is, the higher brain area can affect the primary brain area in turn, regulate its sensitivity and preference, so as to help the brain to understand the external world more finely. Inspired by this, we propose a novel blind image quality index with high-level Semantic Guidance and low-level fine-grained Representation (SGRNet). First, the versatile backbone, called pyramid vision Transformer, is used to simulate the multilevel information processing in the brain, generating multilevel feature representation. Second, we propose a novel high-level semantic guidance module to simulate the feedback mechanism between levels of the visual cortex. Third, a simple but effective fine-grained feature extraction module is proposed for high-level information compensation and lower-level content perception. After this, an attention mechanism-based enhancement module is proposed to further learn the above two features respectively. Finally, a bilinear pooling-based regression module is proposed to integrate the enhanced features of the two parts and map them to the quality score. Extensive experiments on six challenging public datasets show that the proposed SGRNet can deal well with both the simulated and authentic distortions and achieves state-of-the-art performance.