Category · 4 terms
Computer Vision
defined clearly.
How machines perceive images and video — classification, detection, segmentation, generation.
Acronym
advanced
CLIP
OpenAI's 2021 model that learns a joint embedding space for images and text via contrastive training on 400M image-caption pairs.
foundational
Computer Vision
The AI subfield concerned with enabling machines to interpret images and video — object detection, classification, segmentation, tracking, and generation.
intermediate
Image Segmentation
Assigning a class label to every pixel in an image — separating regions like road, building, or pedestrian.
intermediate
Object Detection
A computer vision task that locates and classifies multiple objects in an image, returning bounding boxes and class labels for each.