DenseNet: Implementing Efficient ConvNet Descriptor Pyramids
Forrest Iandola, Matthew W. Moskewicz, Sergey Karayev et al. · arXiv (Cornell University) · 2014
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 629 works. doi:10.48550/arxiv.1404.1869 Open-access PDF
Authors
References
- Backpropagation Applied to Handwritten Zip Code Recognition
- Histograms of Oriented Gradients for Human Detection
- The Pascal Visual Object Classes (VOC) Challenge
- Object Detection with Discriminatively Trained Part-Based Models
- Selective Search for Object Recognition
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Deep Neural Networks for Object Detection
- Describing people: A poselet-based approach to attribute classification
- Exact Acceleration of Linear Object Detectors
- Fast Image Scanning with Deep Max-Pooling Convolutional Neural Networks