I use this repository to document my "deep dive" (:D) into the deep learning literature. I'm starting this repository as a way to document the literature review required by my master thesis in a systematic way. I would like to thank Patrick Liu for inspiring me to make this repository.
Each paper I read should be accompanied by some notes explaining what I've learned from the paper. I will follow a (slightly) modified version of this guide on how to read a scientific paper. Therefore, I will indicate a rough guideline of how much time I spent on each paper to indicate what questions have and have not been answered in the summary.
To make it as easy as possible to stick to this level of self-documentation
this repository contains 2 helpful scripts which generate a baseline summary
to the repository and can edit this README. See scripts/new_summary.py and scripts/update_readme.py.
Feel free to fork and re-use :)!
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks - summary - 300 minutes
- Fast R-CNN - summary - 240 minutes
- Real-time Joint Object Detection and Semantic Segmentation Network for Automated Driving - summary - 180 minutes
- Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss - summary - 180 minutes
- Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving - summary - 180 minutes
- MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving - summary - 300 minutes
- An Overview of Multi-Task Learning in Deep Neural Networks - summary - 180 minutes
- Rich feature hierarchies for accurate object detection and semantic segmentation - summary - 300 minutes
- YOLO9000: Better, Faster, Stronger - summary - 180 minutes
- You Only Look Once: Unified, Real-Time Object Detection - summary - 180 minutes