Elastic ResNeXt Block

Introduced by Wang et al. in ELASTIC: Improving CNNs with Dynamic Scaling Policies

An Elastic ResNeXt Block is a modification of the ResNeXt Block that adds downsamplings and upsamplings in parallel branches at each layer. It is called "elastic" because each layer in the network is flexible in terms of choosing the best scale by a soft policy.

Source: ELASTIC: Improving CNNs with Dynamic Scaling Policies

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
General Classification	1	33.33%
Multi-Label Classification	1	33.33%
Semantic Segmentation	1	33.33%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
1x1 Convolution	Convolutions
Average Pooling	Pooling Operations
Batch Normalization	Normalization
Convolution	Convolutions
Grouped Convolution	Convolutions
ReLU	Activation Functions
Residual Connection	Skip Connections

Categories

Add Remove

Skip Connection Blocks

Image Model Blocks