DACB-Net：用于皮肤病分类的双注意力引导紧凑双线性卷积神经网络
DACB-Net: Dual Attention Guided Compact Bilinear Convolution Neural Network for Skin Disease Classification
AI总结：
本文提出三分支双注意力引导紧凑双线性CNN（DACB-Net），通过全局与局部特征融合、新颖损失函数及迁移学习解决皮肤病分类中的数据不平衡和过拟合问题，在HAM10000和ISIC2019上准确率提升2.59%。
摘要：
本文介绍了三分支的双注意力引导紧凑双线性CNN（DACB-Net），重点从疾病特定区域学习以提升准确性和对齐性。一个全局分支补偿丢失的判别性特征，为相关裁剪区域生成注意力热图（AHM）。最后，将全局和局部分支的最后一个池化层拼接以进行微调，为皮肤病诊断所面临的挑战提供了全面的解决方案。尽管当前的CNN采用随机梯度下降（SGD）进行判别性特征学习，使用不同的局部图像块对来计算梯度，并在损失中加入调制因子以在训练期间聚焦复杂数据。然而，这种方法可能导致数据集不平衡、权重调整以及易受过拟合影响。所提出的解决方案结合了两个监督分支和一个新颖的损失函数来解决这些问题，从而提升性能和可解释性。该框架整合了数据增强、迁移学习和微调，以应对数据不平衡问题，从而提高分类性能并降低计算成本。在HAM10000和ISIC2019数据集上的仿真实验证明了该方法的有效性，与最先进技术相比，准确率提高了2.59%。
英文摘要：
This paper introduces the three-branch Dual Attention-Guided Compact Bilinear CNN (DACB-Net) by focusing on learning from disease-specific regions to enhance accuracy and alignment. A global branch compensates for lost discriminative features, generating Attention Heat Maps (AHM) for relevant cropped regions. Finally, the last pooling layers of global and local branches are concatenated for fine-tuning, which offers a comprehensive solution to the challenges posed by skin disease diagnosis. Although current CNNs employ Stochastic Gradient Descent (SGD) for discriminative feature learning, using distinct pairs of local image patches to compute gradients and incorporating a modulation factor in the loss for focusing on complex data during training. However, this approach can lead to dataset imbalance, weight adjustments, and vulnerability to overfitting. The proposed solution combines two supervision branches and a novel loss function to address these issues, enhancing performance and interpretability. The framework integrates data augmentation, transfer learning, and fine-tuning to tackle data imbalance to improve classification performance, and reduce computational costs. Simulations on the HAM10000 and ISIC2019 datasets demonstrate the effectiveness of this approach, showcasing a 2.59% increase in accuracy compared to the state-of-the-art.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
