Convolutional Neural Networks

A ResNeXt repeats a building block that aggregates a set of transformations with the same topology. Compared to a ResNet, it exposes a new dimension, cardinality (the size of the set of transformations) $C$, as an essential factor in addition to the dimensions of depth and width.

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

Source: Aggregated Residual Transformations for Deep Neural Networks

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Object Detection 38 11.66%
Image Classification 28 8.59%
Semantic Segmentation 24 7.36%
General Classification 19 5.83%
Instance Segmentation 15 4.60%
Object 13 3.99%
Classification 8 2.45%
Action Recognition 7 2.15%
Panoptic Segmentation 6 1.84%

Categories