DL之ResNeXt：ResNeXt算法的簡介(論文介紹)、架構詳解、案例應用等配圖集合之詳細攻略

ResNeXt算法的簡介(論文介紹)

              ResNeXt算法是由Facebook研究人員提出，當時何凱明(ResNet算法作者之一)已經在Facebook工作了，

Abstract

       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 .

摘要

       我們提出了一種簡單、高度子產品化的圖像分類網絡結構。我們的網絡是通過重複一個建構塊來建構的，這個建構塊聚合了一組具有相同拓撲結構的轉換。我們的簡單設計了一個同質的多分支體系結構，隻需要設定幾個超參數。這個政策公開了一個新的次元，我們稱之為“基數”（轉換集的大小），它是除深度和寬度次元之外的一個基本因素。在 ImageNet-1K資料集上，我們通過經驗證明，即使在保持複雜度的限制條件下，增加基數也能提高分類精度。此外，當我們增加容量時，增加基數比更深入或更廣泛更有效。我們的模型名為ResNeXt，是我們進入ILSVRC 2016分類任務的基礎，在該任務中我們獲得了第二名。我們進一步研究了 ImageNet-5K集和 COCO檢測集上的ResNet，也顯示出比ResNet對應的更好的結果。代碼和模型在網上公開。

論文

Saining Xie, Ross Girshick, Piotr Dollár, ZhuowenTu, and KaimingHe.

Aggregated residual transformations for deep neural networks. CVPR 2017

https://arxiv.org/abs/1611.05431

ResNeXt算法的架構詳解

DL之ResNeXt：ResNeXt算法的架構詳解

https://yunyaniu.blog.csdn.net/article/details/98103063

ResNeXt算法的案例應用

更新……