This repository contains implementations of moderne AI architectures from research papers.
Each implementation follows this naming format:
{paper_alias}_{paper_year}
- R-CNN_2013 - Rich feature hierarchies for accurate object detection and semantic segmentation
- VGG_2014 - Very Deep Convolutional Networks for Large-Scale Image Recognition
- FCN_2014 - Fully Convolutional Networks for Semantic Segmentation
- UNet_2015 - U-Net: Convolutional Networks for Biomedical Image Segmentation
- YOLOv1_2015 - You Only Look Once: Unified, Real-Time Object Detection
- SegNet_2015 - SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
- ResNet_2015 - Deep Residual Learning for Image Recognition
- MobileNetV1_2017 - MobileNets: Efficient Convolutional Nerual Networks for Mobile Vision Applications
- MobileNetV2_2018 - MobileNetV2: Inverted Residuals and Linear Bottlenecks
- SID_2018 - Learning to See in the Dark
- Vision_Transformer_2020 - An Image is Worth 16x16 Words: Transformer for Image Recognition at Scale
- CLIP_2021 - Learning Transferable Visual Models from Natural Language Supervision
- Swin_Transformer_2021 - Hierarchical Vision Transformer Using Shifted Windows
- SwinIR_2021 - SwinIR: Image Restoration Using Swin Transformer
- seq2seq_2014 - Sequence to Sequence Learning with Neural Networks
- Transformer_2017 - Attention Is All You Need
- BERT_2018 - BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding