Spatially Adaptive Computation Time for Residual Networks

Michael Figurnov, Maxwell D. Collins, Yukun Zhu, Li Zhang, Jonathan Huang, Dmitry Vetrov, Ruslan Salakhutdinov

CVPR 2017

doi:10.1109/CVPR.2017.194 /cvpr/2017/figurnov2017cvpr-spatially/

Abstract

This paper proposes a deep learning architecture based on Residual Network that dynamically adjusts the number of executed layers for the regions of the image. This architecture is end-to-end trainable, deterministic and problem-agnostic. It is therefore applicable without any modifications to a wide range of computer vision problems such as image classification, object detection and image segmentation. We present experimental results showing that this model improves the computational efficiency of Residual Networks on the challenging ImageNet classification and COCO object detection datasets. Additionally, we evaluate the computation time maps on the visual saliency dataset cat2000 and find that they correlate surprisingly well with human eye fixation positions.

PDF CVPR Semantic Scholar

Cite

Text

Figurnov et al. "Spatially Adaptive Computation Time for Residual Networks." Conference on Computer Vision and Pattern Recognition, 2017. doi:10.1109/CVPR.2017.194

Markdown

[Figurnov et al. "Spatially Adaptive Computation Time for Residual Networks." Conference on Computer Vision and Pattern Recognition, 2017.](https://mlanthology.org/cvpr/2017/figurnov2017cvpr-spatially/) doi:10.1109/CVPR.2017.194

BibTeX

@inproceedings{figurnov2017cvpr-spatially,
  title     = {{Spatially Adaptive Computation Time for Residual Networks}},
  author    = {Figurnov, Michael and Collins, Maxwell D. and Zhu, Yukun and Zhang, Li and Huang, Jonathan and Vetrov, Dmitry and Salakhutdinov, Ruslan},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2017},
  doi       = {10.1109/CVPR.2017.194},
  url       = {https://mlanthology.org/cvpr/2017/figurnov2017cvpr-spatially/}
}