A Fast Learning Algorithm for Image Segmentation with Max-Pooling Convolutional Networks
This work addresses the problem of slow training times for image segmentation networks, which is incremental as it optimizes an existing method for efficiency.
The paper tackles the computational expense of training MaxPooling Convolutional Networks for image segmentation by introducing a fast algorithm that processes each training image in a single pass, resulting in a 1500-fold speed-up while maintaining excellent performance in applications like steel defect detection.
We present a fast algorithm for training MaxPooling Convolutional Networks to segment images. This type of network yields record-breaking performance in a variety of tasks, but is normally trained on a computationally expensive patch-by-patch basis. Our new method processes each training image in a single pass, which is vastly more efficient. We validate the approach in different scenarios and report a 1500-fold speed-up. In an application to automated steel defect detection and segmentation, we obtain excellent performance with short training times.