Viet-Anh on Software Logo

What is: Bottleneck Residual Block?

SourceDeep Residual Learning for Image Recognition
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The use of a bottleneck reduces the number of parameters and matrix multiplications. The idea is to make residual blocks as thin as possible to increase depth and have less parameters. They were introduced as part of the ResNet architecture, and are used as part of deeper ResNets such as ResNet-50 and ResNet-101.