DenseNet: Implementing Efficient ConvNet Descriptor Pyramids

TitleDenseNet: Implementing Efficient ConvNet Descriptor Pyramids
Publication TypeUnpublished
Year of Publication2014
AuthorsIandola, F., Moskewicz M., Karayev S., Girshick R., Darrell T., & Keutzer K.
Other Numbers3700
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.

URLhttps://www.icsi.berkeley.edu/pubs/vision/densenet14.pdf
Bibliographic Notes

Technical Report, Preprint: arXiv:1404.1869

Abbreviated Authors

F. Iandola, M. Moskewicz, S. Karayev, R. Girshick, T. Darrell, and K. Keutzer

ICSI Research Group

Vision

ICSI Publication Type

Unpublished