Advanced Track · KOAI Subject 3

A1. KOAI Advanced I: Computer Vision

Master the full scope of KOAI Subject 3 (Computer Vision) hands-on. You'll learn to pick and use pretrained models from CNNs to diffusion models, and reach a level where you can train and evaluate classification, detection, segmentation, and generation tasks yourself. This is a high-school-division advanced course for students who have completed F1·F2.

🎯 For: high-school division, F1·F2 completed ⏱ Recommended about 10 hours (1:1) 📘 Syllabus 3-1 🧩 Prerequisite: F1·F2 completion

Published: May 16, 2026 | Last updated: May 16, 2026 · Based on the KOAI 2026 guidelines

At a Glance

Track

Advanced

High-school division competitors

Target

High-school division

F1·F2 completed

Recommended Hours

About 10 hours

For 1:1 · varies 6–14 hours

KOAI Mapping

Full scope of Subject 3

Syllabus 3-1

Learning Goals

By the end of A1, the student will master the full scope of KOAI Subject 3 (Computer Vision) hands-on. The goal is to reach a level where you can pick and use pretrained models from CNNs to diffusion models and train and evaluate classification, detection, segmentation, and generation tasks yourself.

After understanding how convolutional layers work in theory, you'll do transfer learning with pretrained encoders like ResNet and EfficientNet, detect objects with YOLO and DETR, and segment images with U-Net. Going all the way through CLIP, self-supervised learning, GANs, and Stable Diffusion, you'll conquer the full range of vision with hands-on code. An advanced trackIt is.

Who It's For & Prerequisites

Recommended for students who

  • Students who have completed F1·F2 (or have equivalent skills)
  • Students preparing to compete in the KOAI high-school division
  • Students who want to dig deep into computer vision with hands-on code
  • Students who want to finish the advanced track by running it alongside A2 (NLP & Audio)

Prerequisites

F1·F2 completion (or equivalent skills) is Required. A foundation in neural networks and deep learning is assumed so you can move straight into CNNs and pretrained models. Recommended only for students planning to compete in the high-school division, and A2can run in parallel with it.

Week-by-Week Curriculum

Below is the standard plan for 1:1. Depending on the student's prior knowledge and pace, some weeks may be accelerated, compressed, or covered in more depth. Core tools: PyTorch, torchvision, timm, albumentations, Ultralytics YOLO, Hugging Face, diffusers.

Week Topic Key Deliverable
1Convolutional layers (theory + hands-on), image classification baselineCIFAR-10 CNN
2Pretrained vision encoders (ResNet, EfficientNet) + transfer learningTransfer learning notebook
3Image augmentation (torchvision, albumentations)augmentation ablation
4Object detection: YOLO, SSD, DETRYOLO fine-tuning
5Image segmentation: U-NetMedical and satellite image segmentation
6Vision-text encoder: CLIPzero-shot classification
7Vision self-supervised learning (SimCLR/DINO concepts)self-supervised embeddings
8GAN image generationDCGAN training
9Diffusion models (using Stable Diffusion + theory)Text→image generation
10Capstone: real-dataset CV projectrepo + demo

※ Weeks are content units; actual time varies by student. Recommended about 10 hours, ranging 6–14 hours.

Assessment & Deliverables

Weekly Deliverables

You'll write a Jupyter notebook each week. You'll train and evaluate classification, detection, segmentation, and generation tasks yourself, and by annotating the English notebooks with key Korean terms, you'll also prepare for the KOAI Round 2 Korean written exam at the same time.

Capstone

You'll complete one ISEF/competition-grade CV project with a real dataset. Packaged as a repo and demo, this result becomes a core pillar of your KOAI portfolio.

Portfolio Impact: Depth Built Over Time

A1 recommends 1 GitHub repo (koai-cv-projects) and 1 Huggingface Spaces demo. The capstone CV project becomes a core pillar of your KOAI portfolio, building up—as an accumulated asset—the kind of depth you can't manufacture in the final weeks before the exam.

GitHub

1 organized repo koai-cv-projects

Huggingface

1 Spaces demo (live demonstration)

Capstone

One ISEF/competition-grade CV project

The capstone CV project is the depth behind the 40% Round 1 document-review portfolio—the core deliverable for KOAI. The earlier you start, the more depth you'll have by the time you compete.

Where This Course Fits

A1 is the first course in the advanced track of the KOAI curriculum. For the full track structure, see KOAI Prep Curriculum Hub.

Previous Step (Prerequisite)

F2. Foundations II

Neural Networks & Deep Learning

Current Course

A1. Advanced I

Computer Vision

Next step

A2. Advanced II

NLP & Audio

Frequently Asked Questions

What do I need to take A1?

You need to have completed F1·F2 (or have equivalent skills). Recommended for students planning to compete in the high-school division.

Can I take A1 and A2 together?

Yes. A1 (CV) and A2 (NLP&Audio) can run in parallel, and both are advanced work in KOAI Subjects 3 and 4.

Which KOAI subject is A1?

It's the full scope of Syllabus Subject 3 (Computer Vision) (3-1). It covers CNNs, transfer learning, object detection, segmentation, CLIP, GANs, and diffusion.

What is the capstone used for?

It's one ISEF/competition-grade CV project, and it becomes a core pillar of the KOAI Round 1 document-review portfolio. We recommend a Huggingface Spaces demo.

What comes after A1?

The order is A2 (NLP&Audio) → C1 Portfolio Studio → C2 Mock Bootcamp → C3 Selection Camp. For exact dates, check the KOAI competition guide (https://citcoding.com/competitions/koai.html).

A1 Consultation

We assess your F1·F2 completion level and design a personalized A1·A2 advanced path for you.

Related Pages

Get a Consultation (02) 540-2922