Feature Enhancement Module Research Articles

Unveiling camouflaged and partially occluded colorectal polyps: Introducing CPSNet for accurate colon polyp segmentation

Background:Segmenting colorectal polyps presents a significant challenge due to the diverse variations in their size, shape, texture, and intricate backgrounds. Particularly demanding are the so-called “camouflaged” polyps, which are partially concealed by surrounding tissues or fluids, adding complexity to their detection. Methods:We present CPSNet, an innovative model designed for camouflaged polyp segmentation. CPSNet incorporates three key modules: the Deep Multi-Scale-Feature Fusion Module, the Camouflaged Object Detection Module, and the Multi-Scale Feature Enhancement Module. These modules work collaboratively to improve the segmentation process, enhancing both robustness and accuracy. Results:Our experiments confirm the effectiveness of CPSNet. When compared to state-of-the-art methods in colon polyp segmentation, CPSNet consistently outperforms the competition. Particularly noteworthy is its performance on the ETIS-LaribPolypDB dataset, where CPSNet achieved a remarkable 2.3% increase in the Dice coefficient compared to the Polyp-PVT model. Conclusion:In summary, CPSNet marks a significant advancement in the field of colorectal polyp segmentation. Its innovative approach, encompassing multi-scale feature fusion, camouflaged object detection, and feature enhancement, holds considerable promise for clinical applications.

Diffusion model-based text-guided enhancement network for medical image segmentation

In recent years, denoising diffusion models have achieved remarkable success in generating pixel-level representations with semantic values for image generation modeling. In this study, we propose a novel end-to-end framework, called TGEDiff, focusing on medical image segmentation. TGEDiff fuses a textual attention mechanism with the diffusion model by introducing an additional auxiliary categorization task to guide the diffusion model with textual information to generate excellent pixel-level representations. To overcome the limitation of limited perceptual fields for independent feature encoders within the diffusion model, we introduce a multi-kernel excitation module to extend the model’s perceptual capability. Meanwhile, a guided feature enhancement module is introduced in Denoising-UNet to focus the model’s attention on important regions and attenuate the influence of noise and irrelevant background in medical images. We critically evaluated TGEDiff on three datasets (Kvasir-SEG, Kvasir-Sessile, and GLaS), and TGEDiff achieved significant improvements over the state-of-the-art approach on all three datasets, with F1 scores and mIoU improving by 0.88% and 1.09%, 3.21% and 3.43%, respectively, 1.29% and 2.34%. These data validate that TGEDiff has excellent performance in medical image segmentation. TGEDiff is expected to facilitate accurate diagnosis and treatment of medical diseases through more precise deconvolutional structural segmentation.

Ancient mural segmentation based on multiscale feature fusion and dual attention enhancement

To address the fuzzy segmentation boundaries, missing details, small target losses and low efficiency of traditional segmentation methods in ancient mural image segmentation scenarios, this paper proposes a mural segmentation model based on multiscale feature fusion and a dual attention-augmented segmentation model (MFAM). The model uses the MobileViT network, which integrates a coordinate attention mechanism, as the feature extraction backbone network. It attains global and local expression capabilities through self-attention, class convolution, and coordinate attention and focuses on location information to expand the receptive field and achieve improved feature extraction efficiency. An A_R_ASPP feature enhancement module is proposed for the attention-optimized residual atrous spatial pyramid pooling module. The module uses residual connections to solve the small target loss problem in murals caused by the excessive sampling rate of atrous convolution and uses a feature attention mechanism to adaptively adjust the feature map weight according to the channel importance levels. A dual attention-enhanced feature fusion module is proposed for multiscale decoder feature fusion to improve the mural segmentation effect. This module uses a cross-level aggregation strategy and an attention mechanism to weight the importance of different feature levels to obtain multilevel semantic feature representations. The model improves the mean intersection over union (MIoU) by 3.06% and the MPA by 1.81% on a mural dataset compared with other models. The model is proven to be effective at improving the segmentation details, efficiency and small target segmentation results produced for mural images, and a new method is proposed for segmenting ancient mural images.

Learning dual attention enhancement feature for visible–infrared person re-identification

Most previous visible–infrared person re-identification methods emphasized learning modality-shared features to narrow the modality differences, while neglecting the benefits of modality-specific features for feature embedding and narrowing the modality gap. To tackle this issue, our paper designs a method based on dual attention enhancement features to use shallow and deep features simultaneously. We first convert visible images into gray images to alleviate the visual difference. Then, to close the difference between modalities by learning the modality-specific features, we design a shallow feature measurement module, in which we use a class-specific maximum mean discrepancy loss to measure the distribution difference of specific features between two modalities. Finally, we design a dual attention feature enhancement module, which aims to mine more useful context information from modality-shared features to shorter the distance between classes within modalities. Specifically, our model exceeds the current SOTAs on SYSU-MM01, with 66.61% Rank-1 accuracy and 62.86% mAP.

IFE-net: improved feature enhancement network for weak feature target recognition in autonomous underwater vehicles

AbstractThe recognizing underwater targets is a crucial component of autonomous underwater vehicle patrols and detection efforts. In the process of visual image recognition in real underwater environment, the spatial and semantic features of the target often appear to different degrees of loss, and the scarcity of specific types of underwater samples leads to unbalanced data on categories. This kind of problem makes the target features appear weak and seriously affects the accuracy of underwater target recognition. Traditional deep learning methods based on data and feature enhancement cannot achieve ideal recognition effect. Based on the above difficulties, this paper proposes an improved feature enhancement network for weak feature target recognition. Firstly, a multi-scale spatial and semantic feature enhancement module is constructed to extract the feature information of the extraction target accurately. Secondly, this paper solves the influence of target feature distortion on classification through multi-scale feature comparison of positive and negative samples. Finally, the Rank & Sort Loss function was used to train the depth target detection to solve the problem of recognition accuracy under highly unbalanced sample data. Experimental results show that the recognition accuracy of the proposed method is 2.28% and 3.84% higher than that of the existing algorithms in the recognition of underwater fuzzy and distorted target images, which demonstrates the effectiveness and superiority of the proposed method.

YOLOv7-TS: A Traffic Sign Detection Model Based on Sub-Pixel Convolution and Feature Fusion

In recent years, significant progress has been witnessed in the field of deep learning-based object detection. As a subtask in the field of object detection, traffic sign detection has great potential for development. However, the existing object detection methods for traffic sign detection in real-world scenes are plagued by issues such as the omission of small objects and low detection accuracies. To address these issues, a traffic sign detection model named YOLOv7-Traffic Sign (YOLOv7-TS) is proposed based on sub-pixel convolution and feature fusion. Firstly, the up-sampling capability of the sub-pixel convolution integrating channel dimension is harnessed and a Feature Map Extraction Module (FMEM) is devised to mitigate the channel information loss. Furthermore, a Multi-feature Interactive Fusion Network (MIFNet) is constructed to facilitate enhanced information interaction among all feature layers, improving the feature fusion effectiveness and strengthening the perception ability of small objects. Moreover, a Deep Feature Enhancement Module (DFEM) is established to accelerate the pooling process while enriching the highest-layer feature. YOLOv7-TS is evaluated on two traffic sign datasets, namely CCTSDB2021 and TT100K. Compared with YOLOv7, YOLOv7-TS, with a smaller number of parameters, achieves a significant enhancement of 3.63% and 2.68% in the mean Average Precision (mAP) for each respective dataset, proving the effectiveness of the proposed model.

DBNet-SI: Dual branch network of shift window attention and inception structure for skin lesion segmentation

The U-shaped convolutional neural network (CNN) has attained remarkable achievements in the segmentation of skin lesion. However, given the inherent locality of convolution, this architecture cannot capture long-range pixel dependencies and multiscale global contextual information effectively. Moreover, repeated convolutions and downsampling operations can readily result in the omission of intricate local fine-grained details. In this paper, we proposed a U-shaped network (DBNet-SI) equipped with a dual-branch module that combines shift window attention and inception structures. First, we proposed a dual-branch module that combines shift window attention and inception structures (MSI) to better capture multiscale global contextual information and long-range pixel dependencies. Specifically, we have devised a cross-branch bidirectional interaction module within the MSI module to enable information complementarity between the two branches in the channel and spatial dimensions. Therefore, MSI is capable of extracting distinguishing and comprehensive features to accurately identify the skin lesion boundaries. Second, we have devised a progressive feature enhancement and information compensation module (PFEIC), which progressively compensates for fine-grained features through reconstructed skip connections and integrated global context attention modules. The results of the experiment show the superior segmentation performance of DBNet-SI compared with other deep learning models for skin lesion segmentation in the ISIC2017 and ISIC2018 datasets. Ablation studies demonstrate that our model can effectively extract rich multiscale global contextual information and compensate for the loss of local details.

Small Object Detection in Remote Sensing Based on Contextual Information and Attention

<p>Many small objects, for instance vehicles and small ships, are encountered in remotely sensed images. However, small object detection has been a challenging task in remote sensing because of the problem that small objects are easily missed and influenced by the background. To address this challenge, we propose a detection method based on contextual information and attention, divided into two main parts. Firstly, for purpose of further improve the backbone network features to derive more contextual information, a multi-branch feature enhancement module is constructed to fuse multiple sensory field features to improve the ability of the backbone network to extract feature information; secondly, a new effective channel attention mechanism is proposed to reduce problems such as information confusion caused by the feature fusion process, thus reducing the influence of the background. Compared with other methods, it effectively improves the detection of small object among remote sensing images.</p> <p> </p>

Swin-Net: A Swin-Transformer-Based Network Combing with Multi-Scale Features for Segmentation of Breast Tumor Ultrasound Images

Breast cancer is one of the most common cancers in the world, especially among women. Breast tumor segmentation is a key step in the identification and localization of the breast tumor region, which has important clinical significance. Inspired by the swin-transformer model with powerful global modeling ability, we propose a semantic segmentation framework named Swin-Net for breast ultrasound images, which combines Transformer and Convolutional Neural Networks (CNNs) to effectively improve the accuracy of breast ultrasound segmentation. Firstly, our model utilizes a swin-transformer encoder with stronger learning ability, which can extract features of images more precisely. In addition, two new modules are introduced in our method, including the feature refinement and enhancement module (RLM) and the hierarchical multi-scale feature fusion module (HFM), given that the influence of ultrasonic image acquisition methods and the characteristics of tumor lesions is difficult to capture. Among them, the RLM module is used to further refine and enhance the feature map learned by the transformer encoder. The HFM module is used to process multi-scale high-level semantic features and low-level details, so as to achieve effective cross-layer feature fusion, suppress noise, and improve model segmentation performance. Experimental results show that Swin-Net performs significantly better than the most advanced methods on the two public benchmark datasets. In particular, it achieves an absolute improvement of 1.4–1.8% on Dice. Additionally, we provide a new dataset of breast ultrasound images on which we test the effect of our model, further demonstrating the validity of our method. In summary, the proposed Swin-Net framework makes significant advancements in breast ultrasound image segmentation, providing valuable exploration for research and applications in this domain.

Joint-Module Health Status Recognition for an Unmanned Platform: A Time–Frequency Representation and Extraction Network-Based Approach

Due to the complex structure of the joint module and harsh working conditions of unmanned platforms, the fault information is often overwhelmed by noise. Moreover, traditional mechanical health state recognition methods usually require a large amount of labeled data in advance, which is difficult to obtain for specific fault data in engineering applications. This limited amount of fault data restricts the diagnostic performance. Additionally, the characteristics of convolutional neural networks (CNNs) limit their ability to capture the relative positional information of fault features. In order to obtain more comprehensive fault information, this paper proposes an intelligent health state recognition method for unmanned platform joint modules based on feature modal decomposition (FMD) and the enhanced capsule network. Firstly, the collected vibration signals are decomposed into a series of feature modal components using FMD. Then, time–frequency maps containing significant fault features are generated based on the continuous wavelet transform (CWT). Finally, a multi-scale feature enhancement (MLFE) module and an efficient channel attention (ECA) module are proposed to enhance the feature extraction capability of the capsule network, extracting more comprehensive global and local feature information from the time–frequency maps to achieve the intelligent state recognition of joint modules. This approach enhances fault features while reducing the impact of redundant features, significantly improving the feature extraction capability without increasing the model’s computational complexity. The effectiveness and superiority of the proposed method are validated through experiments on an unmanned platform joint-module testbed. An ablation experiment demonstrates the effectiveness of the MLFE and ECA modules, and a comparison with other advanced network models proves the superiority of the proposed method for health status recognition.

Dense Connected Edge Feature Enhancement Network for Building Edge Detection from High Resolution Remote Sensing Imagery

Deep-learning-based methods for building-edge-detection have been widely researched and applied in the field of image processing. However, these methods often emphasis the analysis of deep features, which may result in neglecting crucial shallow information representation. Furthermore, abstract features in the deep layers can potentially interfere with the accuracy of edge extraction. To address these challenges, we propose a densely connected edge-detection enhancement network (DCEFE-Net) for building-edge-detection in high-resolution remote sensing images. Firstly, by introducing spatial land channel attention modules, we effectively captured low-level spatial information and high-level semantic information from the input image. Secondly, the proposed edge-aware feature enhancement (EAFE) module emphasis the representation of informative edge features. By alliteratively generating multiple layers of edge-detection maps, it addresses the issue of edge detail loss and enhances edge-detection accuracy. Finally, the dense connectivity blocks strengthen the connections between the convolutional layers, thereby preventing the loss of edge features. Experimental results on the WHU and the Inria Aerial Image Labeling datasets validate the effectiveness of DCEFE-Net, as it consistently produces clear and reliable building-edge results.

TransDD: A transformer-based dual-path decoder for improving the performance of thoracic diseases classification using chest X-ray

Manually and accurately detecting thoracic diseases from CXR images is a time-consuming task that requires experienced radiologists. Therefore, automated thoracic diseases classification has great significance. However, most existing methods solely leverage the feature maps extracted from CXR images to classify thoracic diseases, without effectively connecting the correlation between the local discriminative lesion features and their corresponding labels. To address this issue, we innovatively introduce a learnable label embedding as queries to detect and match class-related features from the feature maps, and then processed by a novel Transformer-based dual-path decoder (TransDD) to facilitate interaction. The proposed TransDD is comprised of three key components: spatial reduction attention (SRA), dual-path attention (DPA), and feature enhancement module (FEM). SRA is employed in simplifying the complexity of self-attention, while DPA is specifically designed to connect the explicit correlation between the features and labels. Moreover, FEM is used to boost the expressiveness of local features. Subsequently, the classification attention block is utilized to balance two classification scores based on the feature output and label output, respectively. The proposed TransDD-PVT attained SOTA performance on the ChestX-ray14 dataset, achieving a mean area under the receiver operating characteristic (AUC) of 83.1% across all 14 classes. Also, our method achieves 94.31% accuracy and 93.31% sensitivity on three-class classifications. Extensive experiments conducted on several datasets demonstrate the powerful ability of our TransDD to improve the performance of thoracic diseases classification. It can serve as a plug-and-play structure to improve the classification performance of both CNNs and recent Transformer-based backbones.

A real-time anchor-free defect detector with global and local feature enhancement for surface defect detection

Industrial surface defect detection (ISDD) is vital for manufacturing enterprises to control product quality. Many general object detection (GOD) methods are utilized in this field. However, they rarely take into full account the characteristics of industrial defects. We identify three crucial characteristics in ISDD: complex background, small size defect and irregular shape. To copy with it, in this paper, we proposed a novel real-time anchor-free defect detector for ISDD. Firstly, to reduce noise interfere from complex background, we proposed global feature enhancement module (GFEM) to enhance high-level feature’s ability in modeling global information so that background noises are alleviated. Secondly, to enhance small size defect’s feature, we introduced local feature enhancement module (LFEM). It enhances small size defect’s feature by amplifying local peaks in low-level features. Thirdly, we introduced box refinement module (BRM) to capture defect’s shape information to provide more accurate prediction result. Lastly, we evaluated the proposed defect detector’s effectiveness using three public ISDD datasets. The experimental results are promising: our detector achieves a mAP of 92.0% on PVEL_AD, 99.6% on the PCB defect dataset, and 81.6% on NEU-DET. These scores outperform state-of-the-art methods, proving the superiority of our proposed detector. Additionally, it reached 46.1 FPS on the PVEL_AD dataset, showing its capability for real-time detection.

ASFFuse: Infrared and visible image fusion model based on adaptive selection feature maps

Researchers continuously modify deep learning network architecture for improved fusion results. However, little attention is given to the influence of noise feature maps generated during the convolution process on the fusion outcomes. Here, we aim to minimize the influence of noisy feature maps on fusion results and propose a fusion model, the infrared and visible image fusion model based on adaptive selection feature maps (ASFFuse). We propose an adaptive selection feature maps module (ASFM). ASFM measures the amount of information contained in each feature map and filters out feature maps that contain more noise information. Additionally, we introduce a feature enhancement module (FEM) to enrich the fusion image with more source image information. For unsupervised training of the proposed model, we propose a texture loss function based on contrast learning. This loss function preserves the texture information of the image in a better way and makes the fusion image have a better visual effect. Our ASFFuse model has been shown to outperform state-of-the-art models in both quantitative and qualitative evaluations in extensive experiments on the TNO and RoadScene datasets. The code is available at https://github.com/LKZ1584905069/ASFFuse.

An object detection algorithm based on infrared-visible dual modal feature fusion

Dual modal image pairs can provide complementary feature information and overcome the limitations of single modal object detection algorithms, thus improving detection performance. In order to fully utilize the features of different modalities, this paper proposes a dual-branch fusion detection network that can simultaneously input both infrared and visible modalities for object detection. The method is based on YOLOv5-s, and two attention modules are proposed according to the characteristics of different modalities to enhance the expression capability of infrared and visible image feature information respectively; At the same time, a dual modal fusion module is designed for cross-modal information complementarity by fusing features from corresponding scales of both modalities; Finally, a feature enhancement module is proposed to improve the multi-scale feature fusion capability. The algorithm is validated on the KAIST, FLIR, and GIR datasets and compared with classic single modal and dual modal detection algorithms. Experimental results show that, compared with the baseline algorithm YOLOv5-s alone detecting visible and infrared images separately, the proposed algorithm improves the detection accuracy by 17.6% and 5.9% on the KAIST dataset respectively, and 19.1% and 13% on the FLIR dataset respectively. The proposed algorithm also has a significant advantage in detection accuracy on the self-built GIR dataset.

Transformer with large convolution kernel decoder network for salient object detection in optical remote sensing images

Despite salient object detection in optical remote sensing images (ORSI-SOD) has made great strides in recent years, it is still a very challenging topic due to various scales and shapes of objects, cluttered backgrounds, and diverse imaging orientations. Most previous deep learning-based methods fails to effectively capture local and global features, resulting in ambiguous localization and semantic information and inaccurate detail and boundary prediction for ORSI-SOD. In this paper, we propose a novel Transformer with large convolutional kernel decoding network, named TLCKD-Net, which effectively models the long-range dependence that is indispensable for feature extraction of ORSI-SOD. First, we utilize Transformer backbone network to perceive global and local details of salient objects. Second, a large convolutional kernel decoding module based on self-attention mechanism is designed for different sizes of salient objects to extract feature information at different scales. Then, a large convolutional refinement and a Salient Feature Enhancement Module are used to recover and refine the saliency features to obtain high quality saliency maps. Extensive experiments on two public ORSI-SOD datasets show that our proposed method outperforms 16 state-of-the-art methods both qualitatively and quantitatively. In addition, a series of ablation studies demonstrate the effectiveness of different modules for ORSI-SOD. Our source code is publicly available at https://github.com/Dpw506/TLCKD-Net.

An Intelligent System of Predicting Lymph Node Metastasis in Colorectal Cancer Using 3D CT Scans

In colorectal cancer (CRC), accurately predicting lymph node metastasis (LNM) contributes to developing appropriate treatment plans and serves as the key to long‐term survival of patients. In the clinical settings, preoperative LNM diagnosis in CRC predominantly depends on computed tomography (CT). Nevertheless, lymph nodes are small in size and difficult to identify on 3D CT scans, and CT‐based diagnosis of metastatic lymph nodes is prone to a significant misdiagnosis rate and lacks consistency across clinicians. Currently, there is no automatic system available for LNM prediction in CRC via 3D CT scans. In addition, existing deep learning‐ (DL‐) based lymph node detection models present low detection accuracy and high false‐positive rates, and most existing DL‐based lymph node metastasis prediction models mainly use tumor area characteristics but fail to adequately utilize lymph node information, thus not yielding satisfactory results. To tackle these issues, we propose an intelligent diagnosis system for this challenging task, mainly including a lymph node detection (LND) model and a lymph node metastasis prediction (LNMP) model. In detail, the LND model utilizes an encoder‐decoder network to detect lymph nodes, and the LNMP model employs an innovative attention‐based multiple instance learning (MIL) network. An instance‐level self‐attention feature enhancement module is designed to extract and augment lymph node features as a bag of instances. Furthermore, a bag‐level MIL prediction module is employed to extract instance features and create a bag representation for the ultimate LNM prediction. As far as we know, the proposed intelligent system represents the pioneering method for addressing this complex clinical challenge. In experiments, our proposed intelligent system achieves the AUC of 75.4% and the accuracy of 73.9%, showcasing a significant enhancement compared to physicians specialising in CRC and highlighting its strong clinical applicability. The accessible code can be found at https://github.com/SCU-MI/IS-LNM.

M2-YOLOX: A Novel Method for Object Detection Based on an Improved YOLOX Algorithm Introducing a Global Attention Mechanism and a Feature Enhancement Module

Deep learning-based algorithms for detecting objects in remote sensing images have produced excellent results recently. However, the target recognition and classification process of remote sensing images has problems such as dense targets, uneven distribution, large-scale changes and complex backgrounds. In order to improve the effectiveness of existing detection methods, based on the YOLOX algorithm, a remote sensing image object detection algorithm introducing Global Attention Mechanism (GAM) and Feature Enhancement Module (FEM) proposed, named the M2-YOLOX(GAM+FEM+YOLOX) algorithm. First, a novel GAM module is developed that employs a sequential channel-space attention mechanism and redesigns the Convolutional Block Attention Module (CBAM), to address the issues of low effective information extraction and weak information representation of the feature map in the backbone network. CBAM is capable of amplifying global dimensional interaction features while reducing information dispersion as well. Second, the goal of the FEM is to improve the target feature extraction capabilities of the backbone feature extraction network by fusing numerous perceptual field features in lower-level feature maps. Then, the Flexible Rectified Linear Unit (FReLU) activation function is introduced under the action of feature fusion and global attention mechanism. Four-way feature map output in Feature Pyramid Networks (FPN) with Non-Maximum Suppression (NMS) and score filtering for object detection and output results. In comparison to the YOLOX algorithm, the experimental results show that the mAP value of the M2-YOLOX algorithm is improved by 0.0123, the LAMR value is decreased by 0.0150, the Precision rate value is increased by 0.105450, the Recall value is increased by 0.053250, and the mF1 value is increased by 0.0425.

Research on fabric defect detection method based on lightweight network

Due to the complexity of fabric texture, the diversity of defect types and the high real-time requirements of textile enterprises, fabric defect detection is faced with considerable challenges. At present, fabric defect detection algorithms based on deep learning have achieved good results, but there are still some key problems to be solved. Firstly, due to the complex construction of deep learning models and high network complexity, it is difficult to meet the real-time requirements of industrial sites, which limits its application in industrial sites. Secondly, in the face of textile enterprises’ requirements for detection accuracy, how to achieve fabric defect detection through a simpler network model, so as to better balance the accuracy and complexity of deep learning models is a major challenge for textile enterprises and academic researchers. In order to solve these problems, a fabric defect detection method based on lightweight network is proposed in this paper. This method takes lightweight network YOLOv5s model as the infrastructure, integrates Convolution Block Attention Module and Feature Enhancement Module in Backbone part and Neck part respectively, and modifies the loss function of YOLOv5s to CIoU_Loss. Compared with the original YOLOv5s, it makes up for the lack of information extraction ability of the network, improves the speed of model inference and the speed and accuracy of prediction box regression. It provides technical support for the application of lightweight network model in industrial field. The performance of the model is tested by using raw fabric and patterned fabric data sets on the deep learning workstation platform. The experimental results show that when the IoU threshold is 0.5, the mean Accuracy Precision mAP of raw fabric and pattern fabric is 86.4% and 75.8%, respectively, which increases by 7.6% and 1.7% compared with the original YOLOv5s algorithm. The average detection speed is as high as 102 FPS, which can meet the real-time requirement of industrial field target detection.

Multiscale Spatial-Temporal Feature Fusion Neural Network for Motor Imagery Brain-Computer Interfaces.

Motor imagery, one of the main brain-computer interface (BCI) paradigms, has been extensively utilized in numerous BCI applications, such as the interaction between disabled people and external devices. Precise decoding, one of the most significant aspects of realizing efficient and stable interaction, has received a great deal of intensive research. However, the current decoding methods based on deep learning are still dominated by single-scale serial convolution, which leads to insufficient extraction of abundant information from motor imagery signals. To overcome such challenges, we propose a new end-to-end convolutional neural network based on multiscale spatial-temporal feature fusion (MSTFNet) for EEG classification of motor imagery. The architecture of MSTFNet consists of four distinct modules: feature enhancement module, multiscale temporal feature extraction module, spatial feature extraction module and feature fusion module, with the latter being further divided into the depthwise separable convolution block and efficient channel attention block. Moreover, we implement a straightforward yet potent data augmentation strategy to bolster the performance of MSTFNet significantly. To validate the performance of MSTFNet, we conduct cross-session experiments and leave-one-subject-out experiments. The cross-session experiment is conducted across two public datasets and one laboratory dataset. On the public datasets of BCI Competition IV 2a and BCI Competition IV 2b, MSTFNet achieves classification accuracies of 83.62% and 89.26%, respectively. On the laboratory dataset, MSTFNet achieves 86.68% classification accuracy. Besides, the leave-one-subject-out experiment is performed on the BCI Competition IV 2a dataset, and MSTFNet achieves 66.31% classification accuracy. These experimental results outperform several state-of-the-art methodologies, indicate the proposed MSTFNet's robust capability in decoding EEG signals associated with motor imagery.