Viet-Anh on Software Logo

What is: ResNeXt Block?

SourceAggregated Residual Transformations for Deep Neural Networks
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

A ResNeXt Block is a type of residual block used as part of the ResNeXt CNN architecture. It uses a "split-transform-merge" strategy (branched paths within a single module) similar to an Inception module, i.e. it aggregates a set of transformations. Compared to a Residual Block, it exposes a new dimension, cardinality (size of set of transformations) CC, as an essential factor in addition to depth and width.

Formally, a set of aggregated transformations can be represented as: F(x)=i=1CTi(x)\mathcal{F}(x)=\sum_{i=1}^{C}\mathcal{T}_i(x), where Ti(x)\mathcal{T}_i(x) can be an arbitrary function. Analogous to a simple neuron, Ti\mathcal{T}_i should project xx into an (optionally low-dimensional) embedding and then transform it.