Fast Image Scanning with Deep Max-Pooling Convolutional Neural Networks

Abstract

Deep Neural Networks now excel at image classification, detection and segmentation. When used to scan images by means of a sliding window, however, their high computational complexity can bring even the most powerful hardware to its knees. We show how dynamic programming can speedup the process by orders of magnitude, even when max-pooling layers are present.

11 pages, 2 figures, 3 tables, 21 references, submitted to ICIP 2013

Cited by in corpus (20)

• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• Deep learning with convolutional neural networks for EEG decoding and visualization
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
• Fully Convolutional Networks for Semantic Segmentation
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• DenseNet: Implementing Efficient ConvNet Descriptor Pyramids
• Fully Connected Deep Structured Networks
• Recent Advances in Deep Learning: An Overview
• Learning to track for spatio-temporal action localization
• Highly Efficient Forward and Backward Propagation of Convolutional Neural Networks for Pixelwise Classification
• Deep Learning Convolutional Networks for Multiphoton Microscopy Vasculature Segmentation
• MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
• Monocular Object Instance Segmentation and Depth Ordering with CNNs
• MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation
• A Fast Face Detection Method via Convolutional Neural Network
• ALCN: Adaptive Local Contrast Normalization
• Convolutional neural networks for segmentation and object detection of human semen
• Dense CNN Learning with Equivalent Mappings
• Deep Co-investment Network Learning for Financial Assets