A Fast Learning Algorithm for Image Segmentation with Max-Pooling Convolutional Networks

Abstract

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.

Cited by in corpus (6)

• Recent Advances in Deep Learning: An Overview
• Deep Learning Convolutional Networks for Multiphoton Microscopy Vasculature Segmentation
• A Multi-Pass Approach to Large-Scale Connectomics
• From Image-level to Pixel-level Labeling with Convolutional Networks
• Toward Streaming Synapse Detection with Compositional ConvNets
• ZNNi - Maximizing the Inference Throughput of 3D Convolutional Networks on Multi-Core CPUs and GPUs