PrincetonComputer SciencePIXL GroupPublications → [Yu et al. 2016] Local Access
Multi-Scale Context Aggregation by Dilated Convolutions

International Conference on Learning Representations (ICLR), May 2016

Fisher Yu, Vladlen Koltun
Abstract

State-of-the-art models for semantic segmentation are based on adaptations of convolutional networks that had originally been designed for image classification. However, dense prediction and image classification are structurally different. In this work, we develop a new convolutional network module that is specifically designed for dense prediction. The presented module uses dilated convolutions to systematically aggregate multi-scale contextual information without losing resolution. The architecture is based on the fact that dilated convolutions support exponential expansion of the receptive field without loss of resolution or coverage. We show that the presented context module increases the accuracy of state-of-the-art semantic segmentation systems. In addition, we examine the adaptation of image classification networks to dense prediction and show that simplifying the adapted network can increase accuracy.
Citation

Fisher Yu and Vladlen Koltun.
"Multi-Scale Context Aggregation by Dilated Convolutions."
International Conference on Learning Representations (ICLR), May 2016.

BibTeX

@inproceedings{Yu:2016:MCA,
   author = "Fisher Yu and Vladlen Koltun",
   title = "Multi-Scale Context Aggregation by Dilated Convolutions",
   booktitle = "International Conference on Learning Representations (ICLR)",
   year = "2016",
   month = may
}