2nd/10_Wiki/Topics/AI_and_ML/Computer_Vision.md

id, title, category, status, canonical_id, aliases, duplicate_of, source_trust_level, confidence_score, verification_status, tags, raw_sources, last_reinforced, github_commit, tech_stack

id	title	category	status	canonical_id	aliases	duplicate_of	source_trust_level	confidence_score	verification_status	tags	raw_sources	last_reinforced	github_commit	tech_stack
wiki-2026-0508-computer-vision	Computer Vision	10_Wiki/Topics	verified	self	CV computer vision image classification object detection segmentation ViT CLIP SAM depth estimation	none	A	0.95	applied	computer-vision deep-learning cnn vit segmentation detection sam clip dino image-classification		2026-05-10	pending	language framework Python PyTorch / Transformers / Detectron2 / Ultralytics / SAM

Computer Vision

매 한 줄

"매 pixel 의 meaning". 매 classification → 매 detection → 매 segmentation → 매 depth → 매 generation. 매 modern: 매 ViT 의 dominant + 매 foundation model (CLIP, SAM, DINOv2). 매 multi-modal LLM 의 vision encoder 의 base.

매 핵심 task

Classification

• 매 image → 매 class.
• 매 ImageNet, 매 ResNet, 매 ViT.

Detection

• 매 image → 매 bbox + class.
• 매 Bounding-Box-Regression 참조.
• 매 YOLO, DETR.

Segmentation

• Semantic: 매 pixel → 매 class.
• Instance: 매 pixel → 매 instance.
• Panoptic: 매 결합.
• 매 SAM (Segment Anything).

Depth estimation

• Monocular: 매 single image → 매 depth.
• Stereo: 매 두 camera.
• 매 MiDaS, Depth Anything.

Pose estimation

• 2D / 3D.
• 매 OpenPose, MediaPipe, ViTPose.

Tracking

• 매 video 의 across frames.
• 매 ByteTrack, BoT-SORT.

Generation

• 매 GAN, Diffusion, Stable Diffusion.
• 매 AI 이미지 생성 및 편집 워크플로우 (AI Image Generation & Editing Workflow) 참조.

OCR

• 매 text from image.
• 매 PaddleOCR, Tesseract, GPT-4V.

Action recognition

• 매 video understanding.

Re-Identification

• 매 person / vehicle re-id.

3D vision

• 매 NeRF, Gaussian Splatting.
• 매 Automated_Mapping 참조.

매 architecture history

CNN era (2012-2020)

• AlexNet (2012) → 매 ImageNet revolution.
• VGG, ResNet (skip connection), DenseNet, EfficientNet.
• 매 inductive bias: locality + translation invariance.

ViT era (2020+)

• ViT (Dosovitskiy 2020).
• 매 patch + transformer.
• 매 large data 의 dominate.
• Swin, DeiT, MAE pretrain.

Foundation model (2021+)

• CLIP: 매 image-text contrastive.
• DINO / DINOv2: 매 self-supervised.
• MAE: 매 masked autoencoder.
• SAM: 매 segment anything.
• Depth Anything: 매 universal depth.

Multi-modal (2023+)

• GPT-4V, Claude vision, Gemini: 매 LLM + vision.
• LLaVA, Qwen-VL: 매 open.
• Sora, Veo: 매 video generation.

💻 패턴

Image classification (ViT, HuggingFace)

from transformers import ViTImageProcessor, ViTForImageClassification
from PIL import Image

processor = ViTImageProcessor.from_pretrained('google/vit-large-patch16-384')
model = ViTForImageClassification.from_pretrained('google/vit-large-patch16-384')

image = Image.open('cat.jpg')
inputs = processor(images=image, return_tensors='pt')
outputs = model(**inputs)
predicted_idx = outputs.logits.argmax(-1).item()
print(model.config.id2label[predicted_idx])

Object detection (YOLO)

from ultralytics import YOLO

model = YOLO('yolov8x.pt')
results = model('image.jpg', conf=0.5)

for r in results:
    for box in r.boxes:
        print(f'{model.names[int(box.cls)]}: {box.conf.item():.2f} at {box.xyxy[0].tolist()}')

Segmentation (SAM)

from segment_anything import sam_model_registry, SamPredictor
import cv2

sam = sam_model_registry['vit_h'](checkpoint='sam_vit_h.pth').to('cuda')
predictor = SamPredictor(sam)
predictor.set_image(image)

# 매 prompt: bbox or point
masks, scores, _ = predictor.predict(
    box=np.array([100, 100, 400, 400]),
    multimask_output=False,
)

Depth estimation (Depth Anything)

from transformers import pipeline

pipe = pipeline('depth-estimation', model='depth-anything/Depth-Anything-V2-Large-hf')
depth = pipe(image)['depth']
depth.save('depth.png')

CLIP zero-shot

import open_clip

model, _, preprocess = open_clip.create_model_and_transforms('ViT-L-14', pretrained='openai')
tokenizer = open_clip.get_tokenizer('ViT-L-14')

candidates = ['a cat', 'a dog', 'a bird']
text = tokenizer(candidates)
img = preprocess(image).unsqueeze(0)

with torch.no_grad():
    img_feat = model.encode_image(img) / ...
    text_feat = model.encode_text(text) / ...
    similarity = (100 * img_feat @ text_feat.T).softmax(-1)

Pose estimation (MediaPipe)

import mediapipe as mp

mp_pose = mp.solutions.pose
with mp_pose.Pose() as pose:
    results = pose.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
    if results.pose_landmarks:
        for lm in results.pose_landmarks.landmark:
            print(lm.x, lm.y, lm.z, lm.visibility)

Tracking (ByteTrack)

from yolox.tracker.byte_tracker import BYTETracker

tracker = BYTETracker(args)
for frame in video:
    detections = detector(frame)  # 매 (N, 5): xyxy + conf
    tracked = tracker.update(detections, frame_size, frame_size)
    for t in tracked:
        print(t.track_id, t.tlbr, t.score)

OCR (PaddleOCR)

from paddleocr import PaddleOCR

ocr = PaddleOCR(use_angle_cls=True, lang='en')
result = ocr.ocr('document.jpg', cls=True)
for line in result[0]:
    bbox, (text, conf) = line
    print(text, conf)

Multi-modal (GPT-4V via API)

from openai import OpenAI
client = OpenAI()

response = client.chat.completions.create(
    model='gpt-4o',
    messages=[{
        'role': 'user',
        'content': [
            {'type': 'text', 'text': 'What objects do you see, and where are they?'},
            {'type': 'image_url', 'image_url': {'url': image_url}},
        ],
    }],
)
print(response.choices[0].message.content)

Self-supervised pre-train (MAE, simplified)

def mae_pretrain(model, image, mask_ratio=0.75):
    patches = patchify(image, patch_size=16)
    n_visible = int(len(patches) * (1 - mask_ratio))
    visible_idx = torch.randperm(len(patches))[:n_visible]
    
    encoded = encoder(patches[visible_idx])
    full = insert_mask_tokens(encoded, visible_idx, total=len(patches))
    reconstructed = decoder(full)
    
    loss = ((reconstructed[masked_idx] - patches[masked_idx]) ** 2).mean()
    return loss

NeRF (volumetric 3D)

# 매 [[Automated_Mapping]] 참조 — 매 NeRF / Gaussian Splatting code

🤔 결정 기준

Task	Tool
Classify	ViT / EfficientNet
Detect	YOLOv8 / DETR / Grounding DINO
Segment	SAM (open-vocab) / Mask2Former
Depth	Depth Anything V2
Pose	MediaPipe / ViTPose
Track	ByteTrack
OCR	PaddleOCR / GPT-4V
Zero-shot	CLIP / SigLIP
Generate	Stable Diffusion / Flux
Edge	YOLOv8n / MobileNetV4
Foundation feature	DINOv2

기본값: 매 task-specific SOTA + 매 CLIP / SAM 의 zero-shot fallback.

🔗 Graph

• 부모: AI · Deep Learning
• 변형: CNN · ViT · CLIP · SAM · MAE
• 응용: Object-Detection · Bounding-Box-Regression · Automated_Mapping · Autonomous Vehicles · Algorithmic-Biology
• Adjacent: Diffusion-Models · CV_Synthesis

🤖 LLM 활용

언제: 매 vision task. 매 multimodal product. 매 image search. 매 autonomous system. 언제 X: 매 audio / pure text. 매 1D signal.

❌ 안티패턴

• Custom CNN from scratch (small data): 매 pretrain 의 use.
• No augmentation: 매 generalization X.
• ImageNet only eval: 매 distribution shift.
• No domain adapt: 매 medical / satellite 의 weak.
• Single model for all task: 매 specialized 의 better.

🧪 검증 / 중복

• Verified (ImageNet, ViT, CLIP, SAM papers).
• 신뢰도 A.
• Related: CLIP · Bounding-Box-Regression · Automated_Mapping · Autonomous Vehicles · CV_Synthesis · Algorithmic-Biology.

🕓 Changelog

날짜	변경
2026-05-08	Phase 1
2026-05-10	Manual cleanup — task taxonomy + history + 매 ViT / YOLO / SAM / Depth / CLIP / GPT-4V code