Landmark 6 stops to get here · leads to 2

Semantic Segmentation

Classifying every pixel in an image into categories, creating a pixel-level understanding of scenes.

Your route here

6 stops · basics first
  1. Machine Learning ✓ understood

    Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.

  2. Supervised Learning ✓ understood

    Learning from examples paired with the correct answer, so a model can predict answers for new inputs it hasn't seen.

  3. Classification ✓ understood

    A supervised learning task where the model assigns each input to one of a fixed set of categories, such as spam or not spam.

  4. Neural Network ✓ understood

    A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons) organized in layers that process information through weighted connections.

  5. Deep Learning ✓ understood

    A subset of machine learning that uses neural networks with multiple layers (deep neural networks) to learn hierarchical representations of data.

  6. Computer Vision ✓ understood

    The field of AI that gets computers to extract meaning from images and video: what is in them, where it is, and how it moves.

  7. Semantic Segmentation · you are here ✓ understood

Picture it

Classification

  • One label for the whole image
  • "This image contains a cat"

Semantic segmentation

  • A class label for every pixel
  • All cat pixels share one label
  • Doesn't separate touching objects

Instance segmentation

  • A label per pixel, plus object identity
  • Cat #1 and cat #2 get separate masks
Notice how semantic segmentation moves from one label per image to one per pixel, but still treats all objects of a class as one region.

Where it sits

Before this

Computer Vision Classification
Semantic Segmentation

Leads to

Instance Segmentation Dice Coefficient

Explore nearby

Vision & Multimodal Instance Segmentation Combining object detection and segmentation to identify individual object instances at the pixel level. Vision & Multimodal U-Net A CNN architecture with encoder-decoder structure and skip connections, widely used for image segmentation tasks. Evaluation Dice Coefficient A metric measuring overlap between predicted and ground truth segmentations, common in medical imaging. Evaluation Intersection over Union A metric for object detection measuring overlap between predicted and ground truth bounding boxes.

In the research

All papers →

A paper that builds on Semantic Segmentation .