A Rotation Meanout Network with Invariance for Dermoscopy Image Classification and Retrieval

by   Yilan Zhang, et al.

The computer-aided diagnosis (CAD) system can provide a reference basis for the clinical diagnosis of skin diseases. Convolutional neural networks (CNNs) can not only extract visual elements such as colors and shapes but also semantic features. As such they have made great improvements in many tasks of dermoscopy images. The imaging of dermoscopy has no main direction, indicating that there are a large number of skin lesion target rotations in the datasets. However, CNNs lack anti-rotation ability, which is bound to affect the feature extraction ability of CNNs. We propose a rotation meanout (RM) network to extract rotation invariance features from dermoscopy images. In RM, each set of rotated feature maps corresponds to a set of weight-sharing convolution outputs and they are fused using meanout operation to obtain the final feature maps. Through theoretical derivation, the proposed RM network is rotation-equivariant and can extract rotation-invariant features when being followed by the global average pooling (GAP) operation. The extracted rotation-invariant features can better represent the original data in classification and retrieval tasks for dermoscopy images. The proposed RM is a general operation, which does not change the network structure or increase any parameter, and can be flexibly embedded in any part of CNNs. Extensive experiments are conducted on a dermoscopy image dataset. The results show our method outperforms other anti-rotation methods and achieves great improvements in dermoscopy image classification and retrieval tasks, indicating the potential of rotation invariance in the field of dermoscopy images.


Efficient and Invariant Convolutional Neural Networks for Dense Prediction

Convolutional neural networks have shown great success on feature extrac...

Clothing Retrieval with Visual Attention Model

Clothing retrieval is a challenging problem in computer vision. With the...

Transform-Invariant Convolutional Neural Networks for Image Classification and Search

Convolutional neural networks (CNNs) have achieved state-of-the-art resu...

What Does CNN Shift Invariance Look Like? A Visualization Study

Feature extraction with convolutional neural networks (CNNs) is a popula...

Flip-Rotate-Pooling Convolution and Split Dropout on Convolution Neural Networks for Image Classification

This paper presents a new version of Dropout called Split Dropout (sDrop...

Empowering Networks With Scale and Rotation Equivariance Using A Similarity Convolution

The translational equivariant nature of Convolutional Neural Networks (C...

Improving the Sample-Complexity of Deep Classification Networks with Invariant Integration

Leveraging prior knowledge on intraclass variance due to transformations...

Please sign up or login with your details

Forgot password? Click here to reset