Geometric Operator Convolutional Neural Network
This work addresses the limitation of CNNs in utilizing domain knowledge for researchers and practitioners in computer vision and medical imaging, though it appears incremental as it builds on existing CNN frameworks.
The paper tackles the problem of CNNs lacking prior domain knowledge by introducing GO-CNN, which replaces the first convolutional layer kernel with a geometric operator function, resulting in improved accuracy on CIFAR-10/100, reduced training data dependence, enhanced adversarial stability, and a 3% recall improvement in bone fracture diagnosis.
The Convolutional Neural Network (CNN) has been successfully applied in many fields during recent decades; however it lacks the ability to utilize prior domain knowledge when dealing with many realistic problems. We present a framework called Geometric Operator Convolutional Neural Network (GO-CNN) that uses domain knowledge, wherein the kernel of the first convolutional layer is replaced with a kernel generated by a geometric operator function. This framework integrates many conventional geometric operators, which allows it to adapt to a diverse range of problems. Under certain conditions, we theoretically analyze the convergence and the bound of the generalization errors between GO-CNNs and common CNNs. Although the geometric operator convolution kernels have fewer trainable parameters than common convolution kernels, the experimental results indicate that GO-CNN performs more accurately than common CNN on CIFAR-10/100. Furthermore, GO-CNN reduces dependence on the amount of training examples and enhances adversarial stability. In the practical task of medically diagnosing bone fractures, GO-CNN obtains 3% improvement in terms of the recall.