Convolutional neural networks at constrained time cost
- 1 June 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5353-5360
- https://doi.org/10.1109/cvpr.2015.7299173
Abstract
Though recent advanced convolutional neural networks (CNNs) have been improving the image recognition accuracy, the models are getting more complex and time-consuming. For real-world applications in industrial and commercial scenarios, engineers and developers are often faced with the requirement of constrained time budget. In this paper, we investigate the accuracy of CNNs under constrained time cost. Under this constraint, the designs of the network architectures should exhibit as trade-offs among the factors like depth, numbers of filters, filter sizes, etc. With a series of controlled comparisons, we progressively modify a baseline model while preserving its time complexity. This is also helpful for understanding the importance of the factors in network designs. We present an architecture that achieves very competitive accuracy in the ImageNet dataset (11.8% top-5 error, 10-view test), yet is 20% faster than “AlexNet” [14] (16.0% top-5 error, 10-view test).Keywords
This publication has 7 references indexed in Scilit:
- CaffePublished by Association for Computing Machinery (ACM) ,2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- CNN Features Off-the-Shelf: An Astounding Baseline for RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Simultaneous Detection and SegmentationLecture Notes in Computer Science, 2014
- Multi-column deep neural networks for image classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Simplifying ConvNets for Fast LearningLecture Notes in Computer Science, 2012
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989