Skip Connection Blocks

Bottleneck Residual Block

Introduced by He et al. in Deep Residual Learning for Image Recognition

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.

Source: Deep Residual Learning for Image Recognition

Papers


Paper Code Results Date Stars

Tasks


Categories