HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentation

Recently, dense connections have attracted substantial attention in computer vision because they facilitate gradient flow and implicit deep supervision during training. Particularly, DenseNet, which connects each layer to every other layer in a feed-forward fashion, has shown impressive performances in natural image classification tasks... (read more)

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Medical Image Segmentation iSEG 2017 Challenge HyperDenseNet Dice Score 0.9257 # 1

Methods used in the Paper


METHOD TYPE
HyperDenseNet
Semantic Segmentation Models
ReLU
Activation Functions
Batch Normalization
Normalization
Convolution
Convolutions
Average Pooling
Pooling Operations
Concatenated Skip Connection
Skip Connections
Global Average Pooling
Pooling Operations
Dense Block
Image Model Blocks
Kaiming Initialization
Initialization
1x1 Convolution
Convolutions
Dropout
Regularization
Max Pooling
Pooling Operations
Softmax
Output Functions
DenseNet
Convolutional Neural Networks
Dense Connections
Feedforward Networks