Fast Image Scanning with Deep Max-Pooling Convolutional Neural Networks

02/07/2013

∙

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.

READ FULL TEXT

Fast Image Scanning with Deep Max-Pooling Convolutional Neural Networks

Comparison of Methods Generalizing Max- and Average-Pooling

Real-time convolutional networks for sonar image classification in low-power embedded systems

Rapid Exact Signal Scanning with Deep Convolutional Neural Networks

Untangling Local and Global Deformations in Deep Convolutional Networks for Image Classification and Sliding Window Detection

The Enhanced Hybrid MobileNet

How is Contrast Encoded in Deep Neural Networks?

Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation

Fast Image Scanning with Deep Max-Pooling Convolutional Neural Networks

Related Research

Comparison of Methods Generalizing Max- and Average-Pooling

Real-time convolutional networks for sonar image classification in low-power embedded systems

Rapid Exact Signal Scanning with Deep Convolutional Neural Networks

Untangling Local and Global Deformations in Deep Convolutional Networks for Image Classification and Sliding Window Detection

The Enhanced Hybrid MobileNet

How is Contrast Encoded in Deep Neural Networks?

Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation