62 lines
3.0 KiB
Plaintext
62 lines
3.0 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "95c6ad63",
|
|
"metadata": {
|
|
"origin_pos": 0
|
|
},
|
|
"source": [
|
|
"# Computer Vision\n",
|
|
":label:`chap_cv`\n",
|
|
"\n",
|
|
"Whether it is medical diagnosis, self-driving vehicles, camera monitoring, or smart filters, many applications in the field of computer vision are closely related to our current and future lives. \n",
|
|
"In recent years, deep learning has been\n",
|
|
"the transformative power for advancing the performance of computer vision systems.\n",
|
|
"It can be said that the most advanced computer vision applications are almost inseparable from deep learning.\n",
|
|
"In view of this, this chapter will focus on the field of computer vision, and investigate methods and applications that have recently been influential in academia and industry.\n",
|
|
"\n",
|
|
"\n",
|
|
"In :numref:`chap_cnn` and :numref:`chap_modern_cnn`, we studied various convolutional neural networks that are\n",
|
|
"commonly used in computer vision, and applied them\n",
|
|
"to simple image classification tasks. \n",
|
|
"At the beginning of this chapter, we will describe\n",
|
|
"two methods that \n",
|
|
"may improve model generalization, namely *image augmentation* and *fine-tuning*,\n",
|
|
"and apply them to image classification. \n",
|
|
"Since deep neural networks can effectively represent images in multiple levels, \n",
|
|
"such layerwise representations have been successfully \n",
|
|
"used in various computer vision tasks such as *object detection*, *semantic segmentation*, and *style transfer*. \n",
|
|
"Following the key idea of leveraging layerwise representations in computer vision,\n",
|
|
"we will begin with major components and techniques for object detection. Next, we will show how to use *fully convolutional networks* for semantic segmentation of images. Then we will explain how to use style transfer techniques to generate images like the cover of this book.\n",
|
|
"In the end, we conclude this chapter\n",
|
|
"by applying the materials of this chapter and several previous chapters on two popular computer vision benchmark datasets.\n",
|
|
"\n",
|
|
":begin_tab:toc\n",
|
|
" - [image-augmentation](image-augmentation.ipynb)\n",
|
|
" - [fine-tuning](fine-tuning.ipynb)\n",
|
|
" - [bounding-box](bounding-box.ipynb)\n",
|
|
" - [anchor](anchor.ipynb)\n",
|
|
" - [multiscale-object-detection](multiscale-object-detection.ipynb)\n",
|
|
" - [object-detection-dataset](object-detection-dataset.ipynb)\n",
|
|
" - [ssd](ssd.ipynb)\n",
|
|
" - [rcnn](rcnn.ipynb)\n",
|
|
" - [semantic-segmentation-and-dataset](semantic-segmentation-and-dataset.ipynb)\n",
|
|
" - [transposed-conv](transposed-conv.ipynb)\n",
|
|
" - [fcn](fcn.ipynb)\n",
|
|
" - [neural-style](neural-style.ipynb)\n",
|
|
" - [kaggle-cifar10](kaggle-cifar10.ipynb)\n",
|
|
" - [kaggle-dog](kaggle-dog.ipynb)\n",
|
|
":end_tab:\n"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"language_info": {
|
|
"name": "python"
|
|
},
|
|
"required_libs": []
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
} |