A DenseNet is a type of convolutional neural network that utilises dense connections between layers, through Dense Blocks, where we connect all layers (with matching feature-map sizes) directly with each other. To preserve the feed-forward nature, each layer obtains additional inputs from all preceding layers and passes on its own feature-maps to all subsequent layers.
Source: Densely Connected Convolutional NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Classification | 71 | 11.68% |
General Classification | 58 | 9.54% |
Classification | 55 | 9.05% |
Semantic Segmentation | 20 | 3.29% |
Object Detection | 15 | 2.47% |
Image Segmentation | 10 | 1.64% |
Computed Tomography (CT) | 9 | 1.48% |
Quantization | 8 | 1.32% |
Multi-Task Learning | 5 | 0.82% |