Video Architecture Search

Posted wangxiaocvpr

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了Video Architecture Search相关的知识,希望对你有一定的参考价值。

Video Architecture Search

2019-10-20 06:48:26

 

This blog is from: https://ai.googleblog.com/2019/10/video-architecture-search.html 

 

技术图片
Examples of various EvaNet architectures. Each colored box (large or small) represents a layer with the color of the box indicating its type: 3D conv. (blue), (2+1)D conv. (orange), iTGM (green), max pooling (grey), averaging (purple), and 1x1 conv. (pink). Layers are often grouped to form modules (large boxes). Digits within each box indicate the filter size.

技术图片
The representative AssembleNet model evolved using the Moments-in-Time dataset. A node corresponds to a block of spatio-temporal convolutional layers, and each edge specifies their connectivity. Darker edges mean stronger connections. AssembleNet is a family of learnable multi-stream architectures, optimized for the target task.
技术图片
A figure comparing AssembleNet with state-of-the-art, hand-designed models on Charades (left) and Moments-in-Time (right) datasets. AssembleNet-50 or AssembleNet-101 has an equivalent number of parameters to a two-stream ResNet-50 or ResNet-101.

技术图片
TinyVideoNet (TVN) architectures evolved to maximize the recognition performance while keeping its computation time within the desired limit. For instance, TVN-1 (top) runs at 37 ms on a CPU and 10ms on a GPU. TVN-2 (bottom) runs at 65ms on a CPU and 13ms on a GPU.
技术图片
CPU runtime of TinyVideoNet models compared to prior models (left) and runtime vs. model accuracy of TinyVideoNets compared to (2+1)D ResNet models (right). Note that TinyVideoNets take a part of this time-accuracy space where no other models exist, i.e., extremely fast but still accurate.

以上是关于Video Architecture Search的主要内容,如果未能解决你的问题,请参考以下文章

论文精读:Neural Architecture Search without Training

Training free Transformer Architecture Search

神经网络搜索Efficient Neural Architecture Search

论文精读:Neural Architecture Search without Training

(转)The Evolved Transformer - Enhancing Transformer with Neural Architecture Search

6s965-fall2022神经架构搜索 Neural Architecture Search