Top 12 Computer Vision GitHub Repositories

Discover the Most Cutting-Edge Computer Vision GitHub Gems

One of the best places to learn and keep following the news in the field of AI & ML is GitHub. There are really impressive GitHub repos that cover the different perspectives of the field starting from study plans, interview questions and answers, important papers, important implementations, and more.

In this article, we will cover 12 of the most important computer vision GitHub repositories that cover a wide range of research and educational topics so as to stay updated with this field and learn new topics under its hood. 

Photo by Roman Synkevych on Unsplash

Table of Contents:

• Awesome Computer Vision

• Computer Vision Tutorials by Roboflow

• Transformer in Vision

• Awesome Referring Image Segmentation

• Awesome Vision Language Pretraining Papers

• Awesome Vision and Language

• Awesome Temporal Action Detection

• Awesome Masked Autoencoders

• Awesome Visual Transformer

• Transformer-Based Visual Segmentation

• CVPR 2023 Paper with Code

• Awesome Deepfakes Detection

---

Looking to start a career in data science and AI and need to learn how. I offer data science mentoring sessions and long-term career mentoring:

• Mentoring sessions: https://lnkd.in/dXeg3KPW

• Long-term mentoring: https://lnkd.in/dtdUYBrM

All the resources and tools you need to teach yourself Data Science for free!

• The best interactive roadmaps for Data Science roles. With links to free learning resources. Start here: https://aigents.co/learn/roadmaps/intro

• The search engine for Data Science learning recourses. 100K handpicked articles and tutorials. With GPT-powered summaries and explanations. https://aigents.co/learn

• Teach yourself Data Science with the help of an AI tutor (powered by GPT-4). https://community.aigents.co/spaces/10362739/

---

1. Awesome Computer Vision

The awesome Computer Vision repo contains a curated list of awesome computer vision resources. These resources include:

• Books

• Courses

• Papers

• Software

• Datasets

• Pre-trained Computer Vision Models

• Tutorials and Talks

• Resources for Students

• Blogs

• Links

2. Computer Vision Tutorials by Roboflow

The Computer Vision Tutorials by Roboflow repo contains computer vision tutorials created by roboflow over the years. This repository contains examples and tutorials on using SOTA computer vision models and techniques. Learn everything from old-school ResNet, through YOLO and object-detection transformers like DETR, to the latest models like Grounding DINO and SAM

3. Transformer in Vision

The Transformer in Vision GitHub repo contains a paper list of some recent Transformer-based CV works which is updated regularly. 

4. Awesome Referring Image Segmentation

The Awesome Referring Image Segmentation GitHub repo contains a collection of referring image segmentation papers and datasets.

5. Awesome Vision Language Pretraining Papers

The Awesome Vision Language Pretraining Papers GitHub repo contains the recent advances in vision and language pretrained models (VL-PTMs).

6. Awesome Vision and Language

The Awesome Vision and Language GitHub repo contains a curated list of awesome vision and language resources. Here is the content of this GitHub repo:

• Survey

• Dataset

• Image Captioning

• Image Retrieval

• Scene Text Recognition (OCR)

• Scene Graph

• text2image

• Video Captioning

• Video Question Answering

• Video Understanding

• Vision and Language Navigation

• Vision and Language Pretraining

• Visual Dialog

• Visual Grounding

• Visual Question Answering (VQA)

• Visual Reasoning

• Visual Relationship Detection

• Visual Storytelling

7. Awesome Temporal Action Detection

The Awesome Temporal Action Detection GitHub repo contains a paper list that covers the following topics:

• Temporal Action Detection 

• Weakly Supervised & Semi-Supervised Temporal Action Detection

• Temporal Action Proposal Generation 

• Open-Vocabulary Temporal Action Detection

8. Awesome Masked Autoencoders

The Awesome Masked Autoencoders GitHub repository is a list of several follow-up research work after or concurrent with MAE to inspire future research. MAE has renewed a surge of interest due to its capacity to learn useful representations from rich unlabeled data. Until recently, MAE and its follow-up works have advanced the state-of-the-art and provided valuable insights into research (particularly vision research). 

9. Awesome Visual Transformer

The Awesome Visual Transformer GitHub repo contains a curated list of transformers for computer vision papers. 

10. Transformer Based Visual Segmentation

The Transformer Based Visual Segmentation repo is used for recording, tracking, and benchmarking several recent transformer-based visual segmentation methods.

11. CVPR 2023 Paper with Code

The CVPR 2023 Paper with Code GitHub repository contains a list of accepted papers to CVPR 2023 with their code. In addition to this, you can find also the previous year's version in the same repository.

12. Awesome Deepfakes Detection

The Awesome Deepfakes Detection GitHub repository contains a list of Deepfakes Detection datasets, tools, papers, and code.

Here is the table of contents of this repository:

• Datasets

• Competitions

• Tools

• Recent Conference Papers

• Survey

• Spatiotemporal Based

• Frequency Based

• Generalization

• Interpretability

• Human-Decision

• Localization

• Multi-modal Based

• Biological Signal

• Fairness

• Fingerprint and Watermark

• Identity-Related

• Adversarial Attack

• Real Scenario

• Anomaly Detection

• Self-Supervised Learning

• Source Model Attribution

• Multiclass Classification

• Federated Learning

• Knowledge Distillation

• Meta-Learning

• Depth Based

Looking to start a career in data science and AI and do not know how. I offer data science mentoring sessions and long-term career mentoring:

• Mentoring sessions: https://lnkd.in/dXeg3KPW

• Long-term mentoring: https://lnkd.in/dtdUYBrM