Aggregated Residual Transformations for Deep Neural Networks

By Saining Xie, Ross B. Girshick, Piotr Doll'ar, Zhuowen Tu, Kaiming He. 2016

11,783 citations recorded by the source corpus.

We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology. Our simple design results in a homogeneous, multi-branch architecture that has only a few hyper-parameters to set. This strategy exposes a new dimension, which we call cardinality (the size of the set of transformations), as an essential factor in addition to the dimensions of depth and width. On the ImageNet-1K dataset, we empirically show that even under the restricted condition of maintaining complexity, increasing cardinality is able to improve classification accuracy. Moreover, increasing cardinality is more effective than going deeper or wider when we increase the capacity. Our models, named ResNeXt, are the foundations of our entry to the ILSVRC 2016 classification task in which we secured 2nd place. We further investigate ResNeXt on an ImageNet-5K set and the COCO detection set, also showing better results than its ResNet counterpart. The code and models are publicly available online.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Quoc V. Le
  2. Jianfeng Gao
  3. Mohit Bansal
  4. Yoshua Bengio
  5. Dacheng Tao
  6. Trevor Darrell
  7. Percy Liang
  8. Sergey Levine

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Ming-Hsuan Yang
  4. Xiaogang Wang
  5. Trevor Darrell
  6. Jitendra Malik
  7. Yi Yang
  8. Alan L. Yuille

In Model Architectures

  1. Quoc V. Le
  2. Alan L. Yuille
  3. Jianfeng Gao
  4. Jiashi Feng
  5. Yoshua Bengio
  6. Shuicheng Yan
  7. Christoph Feichtenhofer
  8. Dacheng Tao

Citations in the corpus