딥러닝 모델 분석과 구현 정리

 

Computer Vision

Tasks	Model	Review	Implementation
Image Classification, Object Detection	AlexNet	AlexNet 논문 리뷰	AlexNet 구현
Image Classification, Object Detection	VGGNet	VGGNet 논문 리뷰	VGGNet 구현
Image Classification, Object Detection	GoogLeNet = Inception v1	GoogLeNet 논문 리뷰	GoogLeNet 구현
Object Detection	R-CNN	R-CNN 논문 리뷰	R-CNN 구현
Object Detection	SPPNet	SPPNet 논문 리뷰	SPPNet 구현
Image Classification	Inception V3	Inception V3 논문 리뷰
Feature Map Visualization	Visualizing and Understanding Convolutional Networks	Visualizing and Understanding Convolutional Networks 논문 리뷰	-
Object Detection	Fast R-CNN	Fast R-CNN 논문 리뷰	-
Image Classification, Object Detection	ResNet	ResNet 논문 리뷰	ResNet 구현
Object Detection	Faster R-CNN	Faster R-CNN 논문 리뷰	Faster R-CNN 구현
Face Recognition,  Face Verification, Re-Identification	FaceNet	FaceNet 논문 리뷰	-
Pose Estimation	DeepPose	DeepPose 논문 리뷰	-
Semantic Segmentation	FCN	FCN 논문 리뷰	-
Semantic Segmentation	DeepLab v1	DeepLab v1 논문 리뷰	-
Semantic Segmentation	U-net	U-net 논문 리뷰	-
Object Detection	YOLO v1	YOLO v1 논문 리뷰	-
Object Detection	CAM	CAM 논문 리뷰	-
Object Detection	SSD	SSD 논문 리뷰	-
Object Detection	DenseNet	DenseNet 논문 리뷰	-
Object Detection Class Imbalance	RetinaNet (Focal Loss)	RetinaNet (Focal Loss) 논문 리뷰	-
Semantic Segmentation	DeepLab v2	DeepLab v2 논문 리뷰	-
Data Augmentation	CutMix	CutMix 논문 리뷰
Object Detection	YOLO v2	YOLO v2 논문 리뷰
Object Detection	FPN	FPN 논문 리뷰
Semantic Segmentation	DeepLab v3	DeepLab V3 논문 리뷰
Image Classification, Object Detection, Face Attributes, Face Recognition, Network Size	MobileNet	MobileNet 논문 리뷰
Image Classification	Squeeze-and-Excitation	Squeeze-and-Excitation 논문 리뷰
Image Classification, Network Size	EfficientNet	EfficientNet 논문 리뷰
Network Structure	NASNet	NASNet 논문 리뷰
Image Classification, Object Detection, Face Attributes, Face Recognition, Network Size	MobileNet V2	MobileNet V2 논문 리뷰
Image Classification	Inception v4	Inception v4 논문 리뷰
Image Classification Depthwise Convolution	Xception	Xception 논문 리뷰
Image Classification, Object Detection, Face Attributes, Face Recognition, Network Size	MobileNet V3	MobileNet V3 논문 리뷰
Object Detection	YOLO v3	YOLO v3 논문 리뷰
Image Classification	ViT (Vision Transformer)	ViT 논문 리뷰
OOD Detector	ODIN	ODIN 논문 리뷰
Human Pose Estimation, Semantic Segmentation, Object Detection	HRNet	HRNet 논문 리뷰
Object Detection Anchor Free	FCOS	FCOS 논문 리뷰
Object Detection	CenterNet
Image Classification, Object Detection, Semantic Segmentation	Swin Transformer	Swin Transformer 논문 리뷰
Image Classification, Network Size	EfficientNet V2	EfficientNet V2 논문 리뷰
Object Detection	YOLO v4	YOLO v4 논문 리뷰
OCR (Optical Chracter Recognition)	CRAFT	CRAFT 논문 리뷰
Object Detection	DETR	DETR 논문 리뷰
Image Classification Network Structure	MLP Mixer
Masked Model Image Classification, Semantic Segmentation	BEiT
Semantic Segmentation	SegFormer
Image Classification	RegNet
View Synthesis	NeRF
	DINO
	MobileViT
	ConvNeXt
	YOLO v6
	YOLO v7
	Mask2Former
	DiT
Generative Model	Stable Diffusion
Generative Model	ControlNet
	Segment Anything
	YOLO v8
	RetNet
	I-JEPA
	YOLO v9
	RT-DETR
	YOLO v10

 

 

NLP

Tasks	Model	Review	Implementation
Classification, Machine Translation, Time Series Prediction	LSTM	LSTM 설명	LSTM 일부 구현
Classification, Machine Translation, Time Series Prediction	GRU	GRU 설명	-
Classification, Machine Translation, Time Series Prediction	Transformer	Transformer 논문 리뷰 및 일부 코드 포함	-
Multiple NL Tasks	BERT	BERT 논문 리뷰	-
Multiple NL Tasks	GPT 1	GPT 논문 리뷰	-
Multiple NL Tasks	RoBERTa	RoBERTa 논문 리뷰	-
Multiple NL Tasks	BART	BART 논문 리뷰	-
Multiple NL Tasks	T5	T5 논문 리뷰	-
Multiple NL Tasks	XLNet	XLNet 논문 리뷰	-
Sentence Embedding	Sentence-BERT	Sentence-BERT 논문 리뷰
Multiple NL Tasks	GPT 2	GPT 2 논문 리뷰	-
Multiple NL Tasks	ELECTRA	ELECTRA 논문 리뷰	-
Attention Mechanism	MQA (Multi-Query Attention)	MQA 논문 리뷰
Activation Function	GLU variants	GLU variants 논문 리뷰
Attention Mechanism	Longformer	Longformer 논문 리뷰
LLM	GPT 3	GPT 3 논문 리뷰
Scaling Law for LM	Scaling Law for LM	Scaling Law for LM 논문 리뷰
Positional Embedding	RoPE	RoPE 논문 리뷰
RAG	RAG	RAG 논문 리뷰
Chain of Thought Prompt Reasoning	CoT	CoT 논문 리뷰
PEFT	LoRA	LoRA 논문 리뷰
LLM	OPT	OPT 논문 리뷰
LLM Data Annotation	LaMDA	LaMDA 논문 리뷰
LLM	GLM
LLM	Gopher
LLM	PaLM	PaLM 논문 리뷰
LLM	BLOOM
Scaling Law for LM	Emergent Abilities of LLM	Emergent Abilities of LLM 논문 리뷰
LLM Scaling Law for LM	Chinchilla	Chinchilla 논문 리뷰
LLM RLHF	InstructGPT	InstructGPT 논문 리뷰
LLM	Self-Instruct	Self-Instruct 논문 리뷰
Chain of Thought Prompt Reasoning	CoT SC	CoT SC 논문 리뷰
LLM	FLAN-T5
LLM	LLaMA	LLaMA 논문 리뷰
LLM	Alpaca
LLM Evaluation	LLM as a Judge	LLM as a Judge 논문 리뷰
Prompt Reasoning	ReAct	ReAct 논문 리뷰
RAG evaluation	RAGAS	RAGAS 논문 리뷰
RAG	Self-RAG	Self-RAG 논문 리뷰
LLM	GPT 4	GPT 4 Technical Report
LLM	LLaMa 2	LLaMA 2 논문 리뷰
Prompt Reasoning	Plan and Solve	Plan and Solve 논문 리뷰
LLM GQA Flash Attention KV Cache	Mistral 7B	Mistral 7B 논문 리뷰
LLM	Falcon	Falcon 논문 리뷰
Prompt Reasoning	Tree of Thought	ToT 논문 리뷰
Long Context	Lost in the Middle	Lost in the Middle 논문 리뷰
Code Generation	CodeGen
Code Generation	Code Llama
Code Generation	StarCoder
RAG	Table Augmented Generation	TAG 논문 리뷰
Prompt Instruction Fine-Tuning	ChartInstruct	ChartInstruct 논문 리뷰
Survey LLM	A Survey of Large Language Model - Wayne Xin Zhao et al (2024)	논문 리뷰
Survey SLM	Small Language Models: Survey, Measurements, and Insights - Zhenyan Lu et al (2024)	논문 리뷰
LLM	Gemma
LLM	Griffin
LLM	Recurrent Gemma
LLM	Falcon Mamba
LLM	LLaMa 3
LLM	Claude 3 Model Family
LLM	Gemma 2
LLM	BLT
LLM MoE	Mixtral
Recurrent Model	RWKV
State Space Model	Mamba
Code Generation	DeepSeek-Coder-V2
Code Generation	Qwen 2.5 Coder
Survey Prompt	A Survey of Prompt Engineering Methods in LLMs for Differenct NLP Tasks - S. Vatsal & H. Dubey (2024)	Vatsal & Dubey 논문 리뷰
Scaling Law for LM	s1: Simple test-time scaling
LLM	LLaMa 4

 

Multimodal

 

Tasks	Model	Review	Implementation
Image Caption Generation	Show and Tell = NIC	NIC 논문 리뷰
Vision-Language Model Zero-shot Image Classification	CLIP	CLIP 논문 리뷰
Vision-Language Model Document Understanding	LayoutLM v1	LayoutLM v1 논문 리뷰
Vision-Language Model Document Understanding	LayoutLM v2	LayoutLM v2 논문 리뷰
Vision-Language Model Document Understanding	LayoutLM v3	LayoutLM v3 논문 리뷰
Zero-shot Vision-Language Model Generative Model	DALL-E	DALL-E 논문 리뷰
Vision-Language Model Document Understanding	Donut	Donut 논문 리뷰
Vision-Language Model	BLIP	BLIP 논문 리뷰
Multimodal LLM	KOSMOS
Multimodal LLM	BLIP-2	BLIP-2 논문 리뷰
Multimodal LLM	Flamingo	Flamingo 논문 리뷰
Multimodal LLM	Video-LLaMA
Multimodal LLM Instruction Fine-Tuning	LLaVA	LLaVA 논문 리뷰
Multimodal LLM	LLaVa 1.5
Multimodal LLM	Gemini
Multimodal LLM	Gemini 1.5
Multimodal LLM	PaliGemma
Multimodal LLM	LLaMA 3.2
Multimodal LLM	Chameleon
Vision-Language Model Document Understanding	olmOCR

 

 

Time Series & Finance

 

Tasks	Model	Review	Implementation
Time Series	HiPPO	HiPPO 논문 리뷰
Time Series	H3
Time Series	Hyena
Time Series	S4
Time Series	Mamba
Time Series	Mamba 2
LLM	BloombergGPT	BloombergGPT 논문 리뷰
LLM	FinGPT	FinGPT 논문 리뷰
Multimodal Financial Data	MFFMs	MFFMS 논문 리뷰

 

 

 

Tabular Data

 

Tasks	Model	Review	Implementation