Soft-Attention Improves Skin Cancer Classification Performance
Datta, S. K.; Shaikh, M. A.; Srihari, S. N.; Gao, M.
Show abstract
In clinical applications, neural networks must focus on and highlight the most important parts of an input image. Soft-Attention mechanism enables a neural network to achieve this goal. This paper investigates the effectiveness of Soft-Attention in deep neural architectures. The central aim of Soft-Attention is to boost the value of important features and suppress the noise-inducing features. We compare the performance of VGG, ResNet, Inception ResNet v2 and DenseNet architectures with and without the Soft-Attention mechanism, while classifying skin lesions. The original network when coupled with Soft-Attention outperforms the baseline[16] by 4.7% while achieving a precision of 93.7% on HAM10000 dataset [25]. Additionally, Soft-Attention coupling improves the sensitivity score by 3.8% compared to baseline[31] and achieves 91.6% on ISIC-2017 dataset [2]. The code is publicly available at github1.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- DermoExpert: Skin lesion classification using a hybrid convolutional neural network through segmentation, transfer learning, and augmentation 98%
- An Inexpensive Smartphone-Based Device and Predictive Models for Rapid, Non-Invasive, and Point-of-Care Monitoring of Ocular and Cardiovascular Complications Related to Diabetes 94%
- EnGRNT: Inference of gene regulatory networks using ensemble methods and topological feature extraction 91%
Similar papers in this journal
- Estimation of Three-Dimensional Chromatin Morphology for Nuclear Classification and Characterisation 96%
- A novel interpretable deep transfer learning combining diverse learnable parameters for improved T2D prediction based on single-cell gene regulatory networks 95%
- Incremental Learning Approach for Semantic Segmentation of Skin Histology Images 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.