Squeeze-and-Excitation Networks

The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial and channel-wise information within local receptive fields at each layer. A broad range of prior research has investigated the spatial component of this relationship, seeking to strengthen the representational power of a CNN by enhancing the quality of spatial encodings throughout its feature hierarchy... (read more)

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification CIFAR-10 SENet + ShakeShake + Cutout Percentage correct 97.88 # 41
Image Classification CIFAR-100 SENet + ShakeEven + Cutout Percentage correct 84.59 # 45

Methods used in the Paper


METHOD TYPE
Average Pooling
Pooling Operations
Global Average Pooling
Pooling Operations
Max Pooling
Pooling Operations
Softmax
Output Functions
Kaiming Initialization
Initialization
Step Decay
Learning Rate Schedules
SGD with Momentum
Stochastic Optimization
Random Horizontal Flip
Image Data Augmentation
Random Resized Crop
Image Data Augmentation
SENet
Convolutional Neural Networks
Dense Connections
Feedforward Networks
ReLU
Activation Functions
Sigmoid Activation
Activation Functions
Squeeze-and-Excitation Block
Image Model Blocks
Convolution
Convolutions