DiCENet is a convolutional neural network architecture that utilizes dimensional convolutions (and dimension-wise fusion). The dimension-wise convolutions apply light-weight convolutional filtering across each dimension of the input tensor while dimension-wise fusion efficiently combines these dimension-wise representations; allowing the DiCE Unit in the network to efficiently encode spatial and channel-wise information contained in the input tensor.
Source: DiCENet: Dimension-wise Convolutions for Efficient NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Classification | 1 | 20.00% |
Object Detection | 1 | 20.00% |
Real-Time Object Detection | 1 | 20.00% |
Real-Time Semantic Segmentation | 1 | 20.00% |
Semantic Segmentation | 1 | 20.00% |