English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

Analyzing the Dependency of ConvNets on Spatial Information

MPS-Authors
/persons/resource/persons242093

Fan,  Yue
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

/persons/resource/persons180947

Xian,  Yongqin
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

/persons/resource/persons243315

Losch,  Max Maria
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

/persons/resource/persons45383

Schiele,  Bernt
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

External Ressource
No external resources are shared
Fulltext (public)

arXiv:2002.01827.pdf
(Preprint), 3MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Fan, Y., Xian, Y., Losch, M. M., & Schiele, B. (2020). Analyzing the Dependency of ConvNets on Spatial Information. Retrieved from https://arxiv.org/abs/2002.01827.


Cite as: http://hdl.handle.net/21.11116/0000-0007-80CB-3
Abstract
Intuitively, image classification should profit from using spatial information. Recent work, however, suggests that this might be overrated in standard CNNs. In this paper, we are pushing the envelope and aim to further investigate the reliance on spatial information. We propose spatial shuffling and GAP+FC to destroy spatial information during both training and testing phases. Interestingly, we observe that spatial information can be deleted from later layers with small performance drops, which indicates spatial information at later layers is not necessary for good performance. For example, test accuracy of VGG-16 only drops by 0.03% and 2.66% with spatial information completely removed from the last 30% and 53% layers on CIFAR100, respectively. Evaluation on several object recognition datasets (CIFAR100, Small-ImageNet, ImageNet) with a wide range of CNN architectures (VGG16, ResNet50, ResNet152) shows an overall consistent pattern.