Description
ShuffleNet V2 Downsampling Block is a block for spatial downsampling used in the ShuffleNet V2 architecture. Unlike the regular ShuffleNet V2 block, the channel split operator is removed so the number of output channels is doubled.
Papers Using This Method
Fragility, Robustness and Antifragility in Deep Learning2023-12-15A Non-monotonic Smooth Activation Function2023-10-16SMU: smooth activation function for deep networks using smoothing maximum technique2021-11-08SAU: Smooth activation function using convolution with approximate identities2021-09-27ErfAct and Pserf: Non-monotonic Smooth Trainable Activation Functions2021-09-09DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks2020-04-22CNN-CASS: CNN for Classification of Coronary Artery Stenosis Score in MPR Images2020-01-23Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks2019-10-21Mish: A Self Regularized Non-Monotonic Activation Function2019-08-23DiCENet: Dimension-wise Convolutions for Efficient Networks2019-06-08Butterfly Transform: An Efficient FFT Based Neural Architecture Design2019-06-05ShuffleNASNets: Efficient CNN models through modified Efficient Neural Architecture Search2018-12-07DSNet for Real-Time Driving Scene Semantic Segmentation2018-12-06ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design2018-07-30