{
  "id": "1808.04303",
  "version": "v1",
  "published": "2018-08-13T15:55:41.000Z",
  "updated": "2018-08-13T15:55:41.000Z",
  "title": "Rank-1 Convolutional Neural Network",
  "authors": [
    "Hyein Kim",
    "Jungho Yoon",
    "Byeongseon Jeong",
    "Sukho Lee"
  ],
  "comment": "The paper is in 2 Column style 8 pages. It will be submitted to CVPR2019",
  "categories": [
    "cs.CV"
  ],
  "abstract": "In this paper, we propose a convolutional neural network(CNN) with 3-D rank-1 filters which are composed by the outer product of 1-D filters. After being trained, the 3-D rank-1 filters can be decomposed into 1-D filters in the test time for fast inference. The reason that we train 3-D rank-1 filters in the training stage instead of consecutive 1-D filters is that a better gradient flow can be obtained with this setting, which makes the training possible even in the case where the network with consecutive 1-D filters cannot be trained. The 3-D rank-1 filters are updated by both the gradient flow and the outer product of the 1-D filters in every epoch, where the gradient flow tries to obtain a solution which minimizes the loss function, while the outer product operation tries to make the parameters of the filter to live on a rank-1 sub-space. Furthermore, we show that the convolution with the rank-1 filters results in low rank outputs, constraining the final output of the CNN also to live on a low dimensional subspace.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-08-13T15:55:41.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "convolutional neural network",
      "outer product operation tries",
      "better gradient flow",
      "gradient flow tries",
      "low dimensional subspace"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 8,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}