DACB-Net: Dual Attention Guided Compact Bilinear Convolution Neural Network for Skin Disease Classification

TL;DR

DACB-Net is a novel dual attention-guided CNN that improves skin disease classification accuracy by focusing on disease-specific regions and addressing dataset imbalance through a combined supervision and loss strategy.

Contribution

The paper introduces DACB-Net, a three-branch CNN with dual attention mechanisms and a new loss function, enhancing skin disease classification accuracy and interpretability.

Findings

Achieved 2.59% higher accuracy than state-of-the-art methods.

Effectively handled dataset imbalance with combined supervision and loss.

Demonstrated improved performance on HAM10000 and ISIC2019 datasets.

Abstract

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.