Computer vision and multimodal learning · MLD-0190
Computer vision
Methods that extract useful structure, predictions, or actions from images and video.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Detect damaged components in manufacturing images.
Original caveat
Vision includes classical methods as well as deep learning.
Context and aliases
Level: Intermediate. Stages: Architecture · Training · Inference.
Tags: DL · Vision · Multimodal.
Aliases: CV.
Related concepts
Concepts linking here
Technology connections
- Albumentations / AlbumentationsX — Image augmentation family with a legacy package and an actively developed AlbumentationsX successor.
- Blender — 3D modeling, rendering and simulation application.
- ComfyUI — Node-based application for generative model workflows.
- Detectron2 — PyTorch-based detection and segmentation framework.
- Kornia — Differentiable computer-vision operations for PyTorch.
- MONAI — PyTorch-based framework for medical imaging AI.
- OpenCV — Computer-vision and image-processing library.
- Pillow — Python image loading, editing and drawing library.
- TorchVision — PyTorch vision datasets, transforms, operators and models.
Original references
- Learning Transferable Visual Models From Natural Language Supervision ↗ · Consulted
- Deep Learning: online textbook ↗ · Consulted
- PyTorch neural-network layers ↗ · Reference link
- Original reference URL ↗