|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/transformers-in-computer-vision-english-version/
课程评论：没有评论
课程名称：计算机视觉中的变压器（英文版） 课程概述： 变压器网络是当前深度学习领域的新趋势。自2017年以来，变压器模型在自然语言处理（NLP）领域引起了轰动，成为几乎所有NLP任务的主流模型。尽管在计算机视觉（CV）领域，变压器的应用相对滞后，但自2020年起开始逐渐成为重要力量。本课程首先介绍注意力机制和变压器网络，在NLP的背景下便于理解。我们将探讨这种架构的优缺点，以及无监督或半监督预训练在变压器架构中的重要性，并简要讨论大型语言模型（LLM），例如BERT和GPT，为变压器在计算机视觉中的应用奠定基础。 接下来，课程将介绍如何将注意力机制扩展到图像的二维空间域，讨论如何利用自注意力推广卷积，以及在编码器-解码器元架构中的应用。同时，我们将展示该架构在图像和文本、NLP中是如何保持一致的，使变压器成为一种通用的函数近似器。此外，我们还将探讨通道和空间注意力、局部与全局注意力等话题。 在接下来的三个模块中，课程将讨论解决计算机视觉中重大问题的特定网络，包括分类、目标检测和分割。我们将讲解来自谷歌的视觉变压器（ViT）、来自微软的窗口变压器（SWIN）、来自Facebook研究的检测变压器（DETR）、分割变压器（SETR）及其他相关技术。同时，讨论变压器在视频处理中的应用，例如时空变压器在移动物体检测和多任务学习中的应用。 最后，课程将展示如何利用著名的Huggingface库，通过Pipeline接口简单地应用这些预训练架构。 此课程为希望深入了解计算机视觉中变压器应用的学习者提供了全面的视角和实用的技能。
Transformer Networks are the new trend in Deep Learning nowadays. Transformer models have taken the world of NLP by storm since 2017. Since then, they become the mainstream model in almost ALL NLP tasks. Transformers in CV are still lagging, however they started to take over since 2020. We will start by introducing attention and the transformer networks. Since transformers were first introduced in NLP, they are easier to be described with some NLP example first. From there, we will understand the pros and cons of this architecture. Also, we will discuss the importance of unsupervised or semi supervised pre-training for the transformer architectures, discussing Large Scale Language Models (LLM) in brief, like BERT and GPT.This will pave the way to introduce transformers in CV. Here we will try to extend the attention idea into the 2D spatial domain of the image. We will discuss how convolution can be generalized using self attention, within the encoder-decoder meta architecture. We will see how this generic architecture is almost the same in image as in text and NLP, which makes transformers a generic function approximator. We will discuss the channel and spatial attention, local vs. global attention among other topics.In the next three modules, we will discuss the specific networks that solve the big problems in CV: classification, object detection and segmentation. We will discuss Vision Transformer (ViT) from Google, Shifter Window Transformer (SWIN) from Microsoft, Detection Transformer (DETR) from Facebook research, Segmentation Transformer (SETR) and many others. Then we will discuss the application of Transformers in video processing, through Spatio-Temporal Transformers with application to Moving Object Detection, along with Multi-Task Learning setup.Finally, we will show how those pre-trained arcthiectures can be easily applied in practice using the famous Huggingface library using the Pipeline interface.
