ConceptAI & ML
Semantic segmentation
A computer vision task where the goal is to classify every single pixel in an input image into a specific category without distinguishing between separate instances of the same class.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Convolutional neural networks3Image classification2Classification1Patch-based processing1Supervised learning1
Opens up
Concepts that name this one as a prerequisite.
Lecturers
3Each in their own terms, from the easiest level.
Fei-Fei Li, Justin Johnson & Serena Yeung
Assigning labels to every pixel in the input image without differentiating object instances.Phillip Isola
A learning task where the output is a per-pixel class label map corresponding to an input image.Sara Beery
The problem of categorizing every individual pixel in an image instead of classifying the whole image as a single category.
Lectures that assume it
1Connections
14The lectures that define it or assume it, and the concepts next to it.
Concepts9
- Convolutional neural networks
- Image classification
- Classification
- Supervised learning
- Instance segmentation
- DatasetGAN