Yolo v1

• 욜로! 혁명의 시작
• Paper : You Only Look Once: Unified, Real-Time Object Detection / code

Yolo v2

• 조금 더 개선된 yolo ?!
• v1에서 v2로 진화 !!
• Paper : YOLO9000: Better, Faster, Stronger

Yolo v3

• 뭐? abox가 10000개라고?
• Paper : YOLOv3: An Incremental Improvement

Yolo v4

• 이제부터 진짜다 !
• 성능을 향상시켜보자!
• Paper : YOLOv4: YOLOv4: Optimal Speed and Accuracy of Object Detection

SAM

• 싹 다 segmentation 해버려!
• Paper : Segment Anything

MobileNet v1

• Mobilenetv1

MobileNet v2

• Mobilenetv2

MobileNet v3

• Mobilenetv3

ResNet

• ResNet
• WideResNet
• Aggregated Residual Transformations for Deep Neural Networks

Transformer

• Transformer를 모르면 취업을 못해요- Attention is all you need

Vision Transformer

• 어텐션을 컴퓨터 비전에? - part1
• 어텐션을 컴퓨터 비전에? - part2
• Paper : An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Efficient ViT

• EfficientViT

Swin Transformer

• ViT를 개선해보자
• Swin Transformer 리뷰
• Paper : Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

TransformerFAM: Feedback attention is working memory - 어텐션! 너 조금씩 깊게 봐봐

• TransformerFAM: Feedback attention is working memory - 어텐션! 너 조금씩 깊게 봐봐

Survey - Sparse Attention

• Sparse한 attention

BERT - 파인튜닝이 젤 중요해!!

⭐️Mamba: Linear-Time Sequence Modeling with Selective State Spaces⭐️ - 맘바 ! Transformer의 대체자 ?

• Mamba

LIME

• “Why Should I Trust You?”
• Paper : “Why Should I Trust You?” Explaining the Predictions of Any Classifier

CAM

• 어이! 너 어딜 보는거야?
• Paper : Learning Deep Features for Discriminative Localization

• 어텐션 플리즈
• Paper : Attention Is All You Need
• code : Transformer

diffusion model *Deep Unsupervised Learning using Nonequilibrium Thermodynamics

• Paper : Deep Unsupervised Learning using Nonequilibrium Thermodynamics

StyleGAN 2019

• styleGAN 2019 - 고해상도 이미지를 고퀄로 생성해보자
• Paper : Analyzing and Improving the Image Quality of StyleGAN

StyleGAN2 ( CVPR2020 )

• styleGAN2(CVPR2020) - StyleGAN의 단점ㅇ을 보완해보자
• Paper : Analyzing and Improving the Image Quality of StyleGAN

xLSTM: Extended Long Short-Term Memory

LSTM을 트랜스포머처럼 만들어보자고 ?

Transformers in Medical Image Analysis - A Review

Swin UNETR

Towards Expert-Level Medical Question Answering with Large Language Models

• Med-PaLM2

Large Language Models Encode Clinical Knowledge

• Med-PaLm

Increased Risks of Open-Angle Glaucoma in Untreated Hypertension

A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics - 헬스케어에 사용되는 LLM들을 조사해보자