2020年计算机视觉技术最新学习路线总结 (含时间分配建议)
点击上方“AI算法与图像处理”,选择加"星标"或“置顶”
重磅干货,第一时间送达
本文转载自:深度学习与计算机视觉
我们的计算机视觉学习路径框架
目标:这个月你会学到什么?关键要点是什么?你的计算机视觉之旅将如何进行?我们会在每个月初提及此问题,以确保你知道该月底的立场以及所处的位置 建议时间:你每周平均应在该部分上花费多少时间 学习资源:该月你将学习的计算机视觉主题的顶级资源集合,其中包括文章,教程,视频,研究论文和其他类似资源
https://discuss.analyticsvidhya.com/t/heres-your-learning-path-to-master-computer-vision-in-2020/87785
2020年成为数据科学家和掌握机器学习的学习之路 https://www.analyticsvidhya.com/blog/2020/01/learning-path-data-scientist-machine-learning-2020 2020年掌握深度学习的学习道路 https://www.analyticsvidhya.com/blog/2020/01/comprehensive-learning-path-deep-learning-2020 自然语言处理(NLP)学习路径 https://www.analyticsvidhya.com/blog/2020/01/learning-path-nlp-2020
第1个月 – 涵盖基础知识:Python与统计
OpenCV中文官方教程v4.1(可选):
http://woshicver.com
https://courses.analyticsvidhya.com/courses/introduction-to-data-science
https://www.khanacademy.org/math/engageny-alg-1/alg1-2
第2个月 – 使用机器学习解决图像分类问题
机器学习基础 https://www.analyticsvidhya.com/blog/2015/06/machine-learning-basics/ sklearn中文官方教程0.22.1(可选): http://sklearn123.com 线性回归 https://www.analyticsvidhya.com/blog/2017/06/a-comprehensive-guide-for-linear-ridge-and-lasso-regression/ 逻辑回归 https://www.analyticsvidhya.com/blog/2015/10/basics-logistic-regression/ 斯坦福大学-机器学习的动机与应用 https://see.stanford.edu/Course/CS229/47 斯坦福大学的“过拟合”和“过拟合”的概念 https://see.stanford.edu/Course/CS229/42
从图像中提取特征的3种技术 https://www.analyticsvidhya.com/blog/2019/08/3-techniques-extract-features-from-image-data-machine-learning-python/ HOG特征 https://www.analyticsvidhya.com/blog/2019/09/feature-engineering-images-introduction-hog-feature-descriptor/ SIFT特征 https://www.analyticsvidhya.com/blog/2019/10/detailed-guide-powerful-sift-technique-image-matching-python/
使用逻辑回归进行图像分类 https://www.kaggle.com/gulsahdemiryurek/image-classification-with-logistic-regression 使用Logistic回归进行图像分类 https://mmlind.github.io/Using_Logistic_Regression_to_solve_MNIST/
https://datahack.analyticsvidhya.com/contest/practice-problem-identify-the-apparels/
第三个月 – Keras和神经网络简介
Keras文档 https://keras.io/ 使用Keras构建神经网络 https://www.analyticsvidhya.com/blog/2016/10/tutorial-optimizing-neural-networks-using-keras-with-image-recognition-case-study/
从零开始的神经网络 https://www.analyticsvidhya.com/blog/2017/05/neural-network-from-scratch-in-python-and-r/ 斯坦福大学神经网络简介 https://youtu.be/d14TUNcbn1k 3Blue1Brown的神经网络: https://youtu.be/aircAruvnKk
https://datahack.analyticsvidhya.com/contest/practice-problem-identify-the-apparels/
第4个月 – 了解卷积神经网络(CNN),迁移学习和参加比赛
卷积神经网络(CNN)简化 https://www.analyticsvidhya.com/blog/2017/06/architecture-of-convolutional-neural-networks-simplified-demystified 斯坦福大学的卷积神经网络: https://youtu.be/bNb2fEVKeEo
掌握迁移学习 https://www.analyticsvidhya.com/blog/2017/06/transfer-learning-the-art-of-fine-tuning-a-pre-trained-model 斯坦福大学实践中的ConvNets: https://youtu.be/dUTzeP_HTZg
DataHack https://datahack.analyticsvidhya.com/contest/all Kaggle https://www.kaggle.com/competitions
第5个月 – 解决对象检测问题
目标检测技术的分步介绍 https://www.analyticsvidhya.com/blog/2018/10/a-step-by-step-introduction-to-the-basic-object-detection-algorithms-part-1 实现faster RCNN用于目标检测 https://www.analyticsvidhya.com/blog/2018/11/implementation-faster-r-cnn-python-object-detection 使用YOLO进行物体检测 https://www.analyticsvidhya.com/blog/2018/12/practical-guide-object-detection-yolo-framewor-python 斯坦福大学的物体检测: https://youtu.be/nDPWywWRIRo YOLO论文 https://arxiv.org/pdf/1506.02640.pdf YOLO预训练模型 https://pjreddie.com/darknet/yolo/
数脸挑战 https://datahack.analyticsvidhya.com/contest/vista-codefest-computer-vision-1 COCO物体检测挑战 http://cocodataset.org/#download
第6个月 – 了解图像分割和注意力模型
图像分割技术的分步介绍 https://www.analyticsvidhya.com/blog/2019/04/introduction-image-segmentation-techniques-python 实现Mask R-CNN进行图像分割 https://www.analyticsvidhya.com/blog/2019/07/computer-vision-implementing-mask-r-cnn-image-segmentation Mask R-CNN论文 https://arxiv.org/pdf/1703.06870.pdf Mask R-CNN GitHub存储库 https://github.com/matterport/Mask_RCNN
http://cocodataset.org/#download
Sequence-to-Sequence Modeling with Attention https://www.analyticsvidhya.com/blog/2018/03/essentials-of-deep-learning-sequence-to-sequence-modelling-with-attention-part-i Sequence-to-Sequence Models by Stanford https://nlp.stanford.edu/~johnhew/public/14-seq2seq.pdf
第7个月 – 探索深度学习工具
PyTorch教程 https://pytorch.org/tutorials/ PyTorch的初学者友好指南 https://www.analyticsvidhya.com/blog/2019/09/introduction-to-pytorch-from-scratch
PyTorch中文官方教程(可选) http://pytorch123.com
TensorFlow:
TensorFlow教程 https://www.tensorflow.org/tutorials TensorFlow简介 https://www.analyticsvidhya.com/blog/2016/10/an-introduction-to-implementing-neural-networks-using-tensorflow
第8个月 – 了解NLP和图像字幕的基础
斯坦福-词嵌入: https://youtu.be/ERibwqs9p38 递归神经网络(RNN)简介: https://youtu.be/UNmqTiOnRfg RNN教程 http://www.wildml.com/2015/10/recurrent-neural-networks-tutorial-part-3-backpropagation-through-time-and-vanishing-gradients/
自动图像字幕 https://cs.stanford.edu/people/karpathy/sfmltalk.pdf 使用深度学习的图像字幕 https://www.analyticsvidhya.com/blog/2018/04/solving-an-image-captioning-task-using-deep-learning
http://cocodataset.org/#download
第9个月 – 熟悉生成对抗网络(GAN)
Ian Goodfellow的生成对抗网络(GAN): https://youtu.be/HGYYEUSm-0Q GAN 论文 https://arxiv.org/pdf/1406.2661.pdf 生成对抗网络的最新进展 https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8667290 Keras-GAN https://github.com/eriklindernoren/Keras-GAN
第10个月 – 视频分析简介
计算视频中演员的放映时间 https://www.analyticsvidhya.com/blog/2018/09/deep-learning-video-classification-python 建立视频分类模型 https://www.analyticsvidhya.com/blog/2019/09/step-by-step-deep-learning-tutorial-video-classification-python 通过视频进行人脸检测 https://www.analyticsvidhya.com/blog/2018/12/introduction-face-detection-video-deep-learning-python
第11个月和第12个月 – 解决项目并参加竞赛
数字识别器 https://www.kaggle.com/c/digit-recognizer ImageNet对象定位挑战 https://www.kaggle.com/c/imagenet-object-localization-challenge 年龄检测 https://datahack.analyticsvidhya.com/contest/practice-problem-age-detection 空中仙人掌鉴定 https://www.kaggle.com/c/aerial-cactus-identification 超声神经分割 https://www.kaggle.com/c/ultrasound-nerve-segmentation 对抗性攻击防御 https://www.kaggle.com/c/nips-2017-defense-against-adversarial-attack/overview
信息图– 2020年计算机视觉学习之路
下载1:动手学深度学习
在「AI算法与图像处理」公众号后台回复:动手学深度学习,即可下载547页《动手学深度学习》电子书和源码。该书是面向中文读者的能运行、可讨论的深度学习教科书,它将文字、公式、图像、代码和运行结果结合在一起。本书将全面介绍深度学习从模型构造到模型训练,以及它们在计算机视觉和自然语言处理中的应用。
个人微信(如果没有备注不拉群!) 请注明:地区+学校/企业+研究方向+昵称
评论