Computer Vision · Intermediate
Computer Vision Engineering
From CNNs to vision transformers: detection, segmentation, tracking and multimodal vision, with the data-engineering discipline real deployments require.
- Level
- Intermediate
- Mathematics depth
- Working
- Engineering depth
- Systems
- Modality
- Cohort-based · lab sessions
- Duration
- Announced per cohort
- Status
- Open for inquiry
Audience
Who this is for
- Engineers building perception features into products
- ML practitioners moving into vision systems
- Robotics and industrial automation engineers
Career paths
Prerequisites
- — Python fluency
- — Working linear algebra
- — Basic ML concepts
Outcomes
Skills acquired
- Select and adapt vision architectures against real constraint sets
- Design labeling and hard-mining loops that keep improving models
- Deploy perception with calibration and confidence handling
Tools used
Curriculum Architecture
Module progression
Expandable, visual, ordered. Each module is a prerequisite-aware step, not an isolated video.
- 01Image Formation & Visual Representation
- 02CNN Architectures & Design Choices
- 03Image Classification at Scale
- 04Object Detection: YOLO & the R-CNN Family
- 05Segmentation & Dense Prediction
- 06Vision Transformers & Attention in Vision
- 07Tracking & Video Understanding
- 08Pose Estimation & Structured Outputs
- 09Multimodal Vision & Language
- 10Deployment, Calibration & Data Engines
Projects
- A detection system with a documented accuracy/latency envelope
- A segmentation pipeline evaluated on hard cases
Assessment philosophy
Assessment is engineering review: written error analyses, measured system behavior, defended design decisions. We evaluate whether you can explain and justify what you built — because production will.
Stack position: Deep Learning → Perception.
FAQ
Frequently asked questions
Do I need a mathematics background?
It depends on the program. Foundation-tier programs start from the mathematics itself; advanced tiers list working linear algebra as a prerequisite. The Mathematics for AI program exists precisely to close that gap.
Is this a bootcamp?
No. CAS Studies is an engineering institute. Programs are built around architectures, derivations and projects with written error analysis — not tutorial replays.
How long does a program take?
The two diploma tracks run on fixed lengths — AI Architectural Engineering spans 18 months, AI Application Engineering spans 1 year. All other program durations are announced per cohort, by modality.
Will I build real systems?
Yes. Every program ends in projects that resemble production work: evaluated models, grounded answer systems, supervised agents — with measurement, not vibes.