Computer Vision
Topic 1 ยท Computer Vision ยท โฑ about 1 h

Computer Vision: Start Here

The main vision tasks, what a junior CV engineer does, the tools of the field, and how this track and its game season are organised.

Show:
In this topic
Beginner

What computer vision covers

Computer vision (CV) is about getting useful information from images and video. Most real projects are one of a few tasks, and choosing the right one is the first design decision:

TaskOutputExample
Classificationone label (or several) per imageWhich type of document is this scan? Is this skin lesion suspicious?
Object detectiona box + label + score for every objectFind every handwritten field on a referral form; count cells in a microscope image.
Semantic segmentationa label for every pixelOutline the tumour in an MRI slice; mark road vs pavement.
Instance segmentationa separate mask for every objectSeparate touching cells; measure each wound.
Keypoints / posecoordinates of landmarksJoint positions for physiotherapy exercises.
Embedding / retrievala vector per imageFind similar X-rays; zero-shot labels with CLIP.
OCRtext and its locationRead the typed parts of a form.

Video adds time (tracking, action recognition), and 3-D adds depth (point clouds, CT volumes); the same building blocks apply.

Beginner

What junior CV roles involve, and the tools

Most day-to-day CV work is not inventing architectures. It is: getting and checking data (labelling guidelines, label quality, splits by patient or site), fine-tuning a pretrained model, evaluating it properly with the task's metric (mAP for detection, Dice/IoU for segmentation), finding failure cases, and making it fast and robust enough to deploy.

The standard tools: PyTorch with torchvision; timm (hundreds of pretrained image models); Ultralytics YOLO and Detectron2 for detection and segmentation; Albumentations for augmentation; OpenCV and Pillow for image processing; MONAI for medical imaging; Hugging Face transformers for ViT, CLIP and segmentation models; labelling tools such as CVAT and Label Studio.

Prerequisite: the Deep Learning track, especially CNNs in depth and transfer learning.

Beginner

How this track is organised

TopicsGame
Images & augmentation ยท Image classification in practice ยท Object detectionC1: Reading the referral forms
Segmentation ยท Vision transformers & CLIP ยท Robustness, fairness & deploymentC2: The wound-care app

As in the Deep Learning track, the browser exercises are in NumPy and the Colab notebooks (09 and 10, below) use PyTorch on a GPU.

Try it

Hands-on: Colab notebooks for this track

09: fine-tune a pretrained classifier with augmentation, Grad-CAM and error analysis. 10: fine-tune an object detector and evaluate it with mAP. Copy a notebook's code into Colab, or upload the .ipynb file.

Interactive: this part runs in your browser.

Check yourself

Quiz

1. You need to measure the area of every individual wound in a photo, even when two touch. Which task?

2. Which task outputs a label for every pixel?

3. Most junior CV work consists mainly ofโ€ฆ

4. Which library is built for medical imaging?

Go deeper

๐Ÿ“š Further reading

Trusted, mostly free sources: official documentation, well-known textbooks and courses. When you want to confirm or go deeper on anything here, start with these.

Ready