This paper proposes a novel method for the automatic diagnosis of keratitis using feature vector quantization and self-attention mechanisms(ADK_FVQSAM).First,high-level features are extracted using the DenseNet121 bac...This paper proposes a novel method for the automatic diagnosis of keratitis using feature vector quantization and self-attention mechanisms(ADK_FVQSAM).First,high-level features are extracted using the DenseNet121 backbone network,followed by adaptive average pooling to scale the features to a fixed length.Subsequently,product quantization with residuals(PQR)is applied to convert continuous feature vectors into discrete features representations,preserving essential information insensitive to image quality variations.The quantized and original features are concatenated and fed into a self-attention mechanism to capture keratitis-related features.Finally,these enhanced features are classified through a fully connected layer.Experiments on clinical low-quality(LQ)images show that ADK_FVQSAM achieves accuracies of 87.7%,81.9%,and 89.3% for keratitis,other corneal abnormalities,and normal corneas,respectively.Compared to DenseNet121,Swin transformer,and InceptionResNet,ADK_FVQSAM improves average accuracy by 3.1%,11.3%,and 15.3%,respectively.These results demonstrate that ADK_FVQSAM significantly enhances the recognition performance of keratitis based on LQ slit-lamp images,offering a practical approach for clinical application.展开更多
Edge deployment solutions based on convolutional neural networks(CNNs)have garnered significant attention because of their potential applications.However,traditional CNNs rely on pooling to reduce the feature size,lea...Edge deployment solutions based on convolutional neural networks(CNNs)have garnered significant attention because of their potential applications.However,traditional CNNs rely on pooling to reduce the feature size,leading to substantial information loss and reduced network robustness.Herein,we propose a more robust adaptive pooling network(APN)method implemented using memristor technology.Our method introduces an improved pooling layer that reduces input features to an arbitrary scale without compromising their importance.Different coupling coefficients of the pooling layer are stored as conductance values in arrays.We validate the proposed APN on generic datasets,demonstrating significant performance improvements over previously reported CNN architectures.Additionally,we evaluate the APN on a CAPTCHA recognition task with perturbations to assess network robustness.The results show that the APN achieves 92.6% accuracy in 4-digit CAPTCHA recognition and exhibits higher robustness.This brief presents a highly robust and novel scheme for edge computing using memristor technology.展开更多
基金supported by the National Natural Science Foundation of China(Nos.62276210,82201148 and 62376215)the Key Research and Development Project of Shaanxi Province(No.2025CY-YBXM-044)+3 种基金the Natural Science Foundation of Zhejiang Province(No.LQ22H120002)the Medical Health Science and Technology Project of Zhejiang Province(Nos.2022RC069 and 2023KY1140)the Natural Science Foundation of Ningbo(No.2023J390)the Ningbo Top Medical and Health Research Program(No.2023030716).
文摘This paper proposes a novel method for the automatic diagnosis of keratitis using feature vector quantization and self-attention mechanisms(ADK_FVQSAM).First,high-level features are extracted using the DenseNet121 backbone network,followed by adaptive average pooling to scale the features to a fixed length.Subsequently,product quantization with residuals(PQR)is applied to convert continuous feature vectors into discrete features representations,preserving essential information insensitive to image quality variations.The quantized and original features are concatenated and fed into a self-attention mechanism to capture keratitis-related features.Finally,these enhanced features are classified through a fully connected layer.Experiments on clinical low-quality(LQ)images show that ADK_FVQSAM achieves accuracies of 87.7%,81.9%,and 89.3% for keratitis,other corneal abnormalities,and normal corneas,respectively.Compared to DenseNet121,Swin transformer,and InceptionResNet,ADK_FVQSAM improves average accuracy by 3.1%,11.3%,and 15.3%,respectively.These results demonstrate that ADK_FVQSAM significantly enhances the recognition performance of keratitis based on LQ slit-lamp images,offering a practical approach for clinical application.
基金supported by the National Natural Science Foundation of China(Grant Nos.62274002,62304001,and 62201005)the Anhui Provincial Natural Science Foundation(Grant Nos.2308085QF213 and 2408085QF211)the Natural Science Research Project of the Anhui Educational Committee(Grant No.2023AH050072)。
文摘Edge deployment solutions based on convolutional neural networks(CNNs)have garnered significant attention because of their potential applications.However,traditional CNNs rely on pooling to reduce the feature size,leading to substantial information loss and reduced network robustness.Herein,we propose a more robust adaptive pooling network(APN)method implemented using memristor technology.Our method introduces an improved pooling layer that reduces input features to an arbitrary scale without compromising their importance.Different coupling coefficients of the pooling layer are stored as conductance values in arrays.We validate the proposed APN on generic datasets,demonstrating significant performance improvements over previously reported CNN architectures.Additionally,we evaluate the APN on a CAPTCHA recognition task with perturbations to assess network robustness.The results show that the APN achieves 92.6% accuracy in 4-digit CAPTCHA recognition and exhibits higher robustness.This brief presents a highly robust and novel scheme for edge computing using memristor technology.
