deep-learning-programming

The assignments of 'Deep Learning Programming' lecture (2024 autumn)

All labs contains

• pre-report: summarizing papers
• ipynb files : implemented algorithm with Pytorch
• final report : analyzing results

All reports are written in English except pre-report of Lab1.

We use latex(Overleaf) and BMVC Paper Templates for writing report.

index

• Lab1: implementing VGGNet and ResNet architectures

  • VGGNet: Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition, 2015
  • ResNet: Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition, 2015.

• Lab2: Object Detection with implementing YOLO architectures

  • YOLO: Joseph Redmon, Santosh Divvala, Ross Girshick and Ali Farhadi. You Only Look Once: Unified, Real-Time Object Detection. 2015

• Lab3: Object Detection with implementing Faster R-CNN architectures

  • Faster R-CNN: Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster rcnn: Towards real-time object detection with region proposal networks, 2016.

• Lab4: Semantic Segmentation with implementing Fully Convolutional Networks.

  • Fully Convolutional Network: Jonathan Long, Evan Shelhamer, and Trevor Darrell. Fully convolutional networks for semantic segmentation, 2015.
  • Learning Deconvolution Network: Hyeonwoo Noh, Seunghoon Hong, and Bohyung Han. Learning deconvolution network for semantic segmentation, 2015

• Lab5: implementing Vision Transformer(ViT) model

  • Vision Transformer: Alexey Dosovitskiy et al. An image is worth 16x16 words: Transformers for image recognition at scale, 2021.

• Lab6: Style Transfer

  • Style Transfer: L. A. Gatys, A. S. Ecker and M. Bethge, "Image Style Transfer Using Convolutional Neural Networks," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 2414-2423, doi: 10.1109/CVPR.2016.265.

• Lab7: implementing Gradient-weighted Class Activation Mapping(Grad-CAM)

  • CAM: Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. Learning deep features for discriminative localization, 2015.
  • Grad-CAM: Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. Grad-cam: Visual explanations from deep networks via gradient-based localization. International Journal of Computer Vision, 128(2):336-359, October 2019.ISSN 1573-1405. doi: 10.1007/s11263-019-01228-7.

• Lab8: implementing CLIP

  • CLIP: Alec Radford et al. Learning transferable visual models from natural language supervision, 2021.
    • ref: Simple Implementation of OpenAI CLIP model: A Tutorial
    • code ref: https://github.com/moein-shariatnia/OpenAI-CLIP

• Lab9: Stable Diffusion fine-tuning with LoRA

  • stable diffusion: Robin Rombach,Andreas Blattmann,Dominik Lorenz,Patrick Esser,and Björn Ommer. High-resolution image synthesis with latent diffusion models, 2022.
  • LoRA : Edward J.Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang,and Weizhu Chen.Lora:Low-rank adaptation of large language models,2021.