Weight normalization [14]isapowerful alternativetoBatchNorm that improvesthe conditioning of neural network training without the need to estimate statistics from neuron inputs.

We demonstrate the algorithm's effectiveness

A.1 Experimental Setting for Skin Lesion Classification T ask A.2 Experimental Setting for Spinal Cord Gray Matter Segmentation T ask The results are shown in Table 1 (a). The results are shown in Table 1 (b). Focal loss for dense object detection.

The study of sparsity in Convolutional Neural Networks (CNNs) has become widespread to compress and accelerate models in environments with limited resources. By constraining N consecutive weights along the output channel to be group-wise non-zero, the recent network with 1$\times$N sparsity has received tremendous popularity for its three outstanding advantages: 1) A large amount of storage space saving by a \emph{Block Sparse Row} matrix.