Paper得来终觉浅，绝知此事要coding。

Knowledge obtained on the papers always feels shallow, and it must be known that this thing requires coding.

Purpose

1. Minimal Practice
2. Project Notes
3. Optimization
4. Algorithm Competition

Basic

1. CNN

Model	Link	Paper	Code
Resnet	Deep Residual Learning for Image Recognition	✅	✅
InceptionV3	Rethinking the Inception Architecture for Computer Vision	✅	✅
InceptionV4	Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning	✅	⬜
MobileNet	MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications	⬜	⬜
EfficientNet	EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks	⬜	⬜
Residual Attention Network	Residual Attention Network for Image Classification	✅	✅
Non-deep Networks	Non-deep Networks	⬜	⬜

2. RNN

Model	Link	Paper	Code
LSTM	Long Short-term Memory	✅	✅
BiLSTM	Bidirectional recurrent neural networks	✅	⬜
GRU	Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation	✅	⬜

3. Transformer

Model	Link	Paper	Code
Transformer	Attention Is All You Need	✅	✅
BERT	BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding	✅	⬜
GPT-3	Language Models are Few-Shot Learners	✅	⬜
ViT	An image is worth 16x16 words: Transformers for image recognition at scale	✅	⬜

4. Generation

Model	Link	Paper	Code
GAN	Generative Adversarial Networks	✅	⬜
pix2pix	Image-to-Image Translation with Conditional Adversarial Networks	⬜	⬜
CycleGAN	Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks	✅	⬜
VAE	Auto-Encoding Variational Bayes	✅	✅
DDPM	Denoising Diffusion Probabilistic Models	✅	⬜
Guided Diffusion	Diffusion Models Beat GANs on Image Synthesis	✅	⬜
DALL.E 2	Hierarchical Text-Conditional Image Generation with CLIP Latents	⬜	⬜

5. Multimodal

Model	Link	Paper	Code
CLIP	Learning Transferable Visual Models From Natural Language Supervision(Connecting Text and Images)	✅	✅
ViLT	ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision	✅	⬜
SimVLM	SimVLM: Simple Visual Language Model Pretraining with Weak Supervision	✅	⬜
ALBEF	Align before Fuse: Vision and Language Representation Learning with Momentum Distillation	✅	✅
VLMo	VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts	✅	⬜
BLIP	BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation	✅	⬜
CYCLIP	CyCLIP: Cyclic Contrastive Language-Image Pretraining	✅	⬜
+MAE	Training Vision-Language Transformers from Captions Alone	✅	⬜
VLMixer	VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix	✅	⬜

Project

1. Object Detection

Model	Link	Paper	Code
R-CNN	Rich feature hierarchies for accurate object detection and semantic segmentation	✅	⬜
Faster R-CNN	Faster R-CNN	✅	⬜
YoloV3	You Only Look Once: Unified, Real-time Object Detection	✅	⬜
DETR	End-to-End Object Detection with Transformers	⬜	⬜

3. Audio-visual

Model	Link	Paper	Code
Syncnet	Out of time: automated lip sync in the wild	✅	⬜
Wav2lip	A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild	✅	✅