Densely Connected Convolutional Networks: CVPR 2017 Best Paper Award Winner

29 points by ChaseT 7 years ago | 3 comments
  • GChevalier 7 years ago
    Seems promising and easy to use in practice.
    • Govindae 7 years ago
      Am I understanding this correctly? The layers do not combine their inputs. Equation (2)

      x_l = H_l([x_0, x_1, . . . , x_l−1])

      Could be re-written: x_l = [H_l(x_0), H_l(x_1), . . . , H_l(x_l−1)]

      • jordancampbell 7 years ago
        No, inputs to each layer are concatenated before being passed through H.