Densely Connected Convolutional Networks: CVPR 2017 Best Paper Award Winner (arxiv.org) 29 points by ChaseT 8y ago ↗ HN
[–] Govindae 8y 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 8y ago ↗ No, inputs to each layer are concatenated before being passed through H.
3 comments
[ 3.2 ms ] story [ 32.3 ms ] threadx_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)]