DenseNet: Implementing Efficient ConvNet Descriptor Pyramids

Abstract

Convolutional Neural Networks (CNNs) can provide accurate object classification. They can be extended to perform object detection by iterating over dense or selected proposed object regions. However, the runtime of such detectors scales as the total number and/or area of regions to examine per image, and training such detectors may be prohibitively slow. However, for some CNN classifier topologies, it is possible to share significant work among overlapping regions to be classified. This paper presents DenseNet, an open source system that computes dense, multiscale features from the convolutional layers of a CNN based object classifier. Future work will involve training efficient object detectors with DenseNet feature descriptors.

Cited by in corpus (5)

• Speeding up Convolutional Neural Networks with Low Rank Expansions
• Pixel-wise Deep Learning for Contour Detection
• Deformable Part Models are Convolutional Neural Networks
• DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection
• Contour Detection Using Cost-Sensitive Convolutional Neural Networks