AI Glossary
The field of AI that enables machines to interpret images and video, for example recognizing objects, reading text or measuring movement.
Applications range from medical imaging and quality inspection in factories to self-driving cars, face recognition and photo search. Typical tasks are classification (what is in the image), detection (where objects are) and segmentation (which pixels belong to each object).
Modern systems increasingly combine vision with language, so you can ask questions about an image in plain words.
The 2015 ResNet paper solved the degradation problem with residual connections and won ImageNet. How skip connections work and why every transformer uses them.
thelatentdaily.com Editorial Team3 min read
In 2020, Google showed that a plain transformer applied to image patches can rival convolutional networks. How ViT works, why it needs lots of data and what it enabled.
thelatentdaily.com Editorial Team4 min read
CLIP learned from 400 million image-caption pairs to match pictures with text, enabling zero-shot image classification and powering text-to-image generators.
thelatentdaily.com Editorial Team4 min read