Sparsely Aggregated Convolutional Networks [PDF]

Ligeng Zhu, Ruizhi Deng, Michael Maire, Zhiwei Deng, Greg Mori, Ping Tan

SparseNet is a network architecture that only aggregates previous layers with exponential offset, for example, i - 1, i - 2, i - 4, i - 8, i - 16 ...

The connectivity pattern yields state-of-the-art arruacies on small dataset CIFAR/10/100. On large scale ILSVRC 2012 (ImageNet) dataset, SparseNet achieves similar accuracy as ResNet and DenseNet, while only using much less parameters.

• Parameter efficiency on CIFAR

• Paramter efficiency on ImageNet

  We notice sparsenet shows comparable efficiency even compared with pruned models.

Refer for source folder.

If SparseNet helps your research, please cite our work :)

@article{DBLP:journals/corr/abs-1801-05895,
  author    = {Ligeng Zhu and
               Ruizhi Deng and
               Michael Maire and
               Zhiwei Deng and
               Greg Mori and
               Ping Tan},
  title     = {Sparsely Aggregated Convolutional Networks},
  journal   = {CoRR},
  volume    = {abs/1801.05895},
  year      = {2018},
  url       = {http://arxiv.org/abs/1801.05895},
  archivePrefix = {arXiv},
  eprint    = {1801.05895},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1801-05895},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}