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 | 70 | 11.90% |
General Classification | 58 | 9.86% |
Classification | 54 | 9.18% |
Semantic Segmentation | 19 | 3.23% |
Object Detection | 15 | 2.55% |
Computed Tomography (CT) | 9 | 1.53% |
Image Segmentation | 9 | 1.53% |
Quantization | 8 | 1.36% |
COVID-19 Diagnosis | 5 | 0.85% |