heitorrapela Goto Github PK

followers: 117.0 following: 243.0 repos: 173.0 gists: 1.0

Name: Heitor Rapela Medeiros

Type: User

Company: ETS Montreal

Bio: PhD Candidate. My interests rely on computer vision, unsupervised learning, representation learning, robotics.

Twitter: HeitorRapela

Location: Montreal, QC

Blog: https://www.linkedin.com/in/heitorrapela/

Hi there, I am Heitor Rapela!

🔭 I’m currently working on my Cross-Modal Detection
🌱 I’m currently learning Pytorch Lightning
📫 How to reach me: @heitorrapela on Twitter
I am 3x Kaggle Expert (with one solo first place in Kaggle TPS)
I am also third year PhD Candidate with publications in top computer vision (CV) conferences
More than 10 years experience in CV

Overview

Hi, I am Heitor Rapela, a Ph.D. student working with cross-modal detection (e.g., RGB <-> Infrared detection). My advisors are Marco Pedersoli and Eric Granger.

During my bachelor's in Computer Engineer, I cofounded the Ardurec Community and the RoboCIn. At this time, I was the computer vision manager of the RoboCIn Very Small Size team.

My undergrad project was about clustering with self-organizing maps using deep learning features. This work granted me a journal (Computer Vision and Image Understanding - CVIU) and helped me build confidence in my research.

In my undergrad and Master's, I was advised by professor Hansenclever Bassani, one of the best researchers that I know. I also worked on many side projects with professor Edna Barros, like detection and recognition projects in CETENE.

After that, I continued working with computer vision but started to learn and apply machine learning techniques in personal projects and academic projects.

I did my Master's degree in the field of unsupervised deep learning, which I developed with my coworker the deep clustering self-organizing maps with relevance learning. You can check in my google scholar papers. I also worked during my Master's with detection, semantic segmentation, and reinforcement learning.

In my spare time, I like to learn and compete @Kaggle.

Languages and Tools

GitHub Stats

Kaggle Stats (Sum of different categories)

Latest Tweets

Heitor Rapela Medeiros's Projects

.tmux

🇫🇷 Oh my tmux! My self-contained, pretty & versatile tmux configuration made with ❤️

6s965-fall2022

ac-fpn

Implement of paper 《Attention-guided Context Feature Pyramid Network for Object Detection》

aligndet

Official code for ICCV 2023 Paper: AlignDet: Aligning Pre-training and Fine-tuning in Object Detection.

animatediff

Official implementation of AnimateDiff.

annotated_deep_learning_paper_implementations

🧑‍🏫 50! Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

anti-uav

🔥🔥Official Repository for Anti-UAV🔥🔥

ap-loss

The implementation of "Towards accurate one-stage object detection with AP-loss".

arduinoworkshop

Material para Curso Básico de Arduino

arxiv-latex-cleaner

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

at-my-home

Hello There, this is my rep to install the right way @home (ROS indigo + Gazebo)

awesome-domain-adaptation-object-detection

A collection of papers about domain adaptation object detection. Welcome to PR the works (papers, repositories) that are missed by the repo.

awesome-prompt-adapter-learning-for-vision-language-models

A curated list of prompt/adapter learning methods for vision-language models.

awesome-rgbt-feature-fusion

A collection of RGB-T-Feature-Fusion methods (deep learning methods mainly), codes, and datasets. The main directions involved are Multispectral Pedestrian, RGB-T Vehicle Detection, RGB-T Crowd Counting, RGB-T Fusion Tracking.

awesome-source-free-test-time-adaptation

A curated list of papers in Test-time Adaptation, Test-time Training and Source-free Domain Adaptation

awesome-test-time-adaptation

Collection of awesome test-time (domain/batch/instance) adaptation methods

awesome-tips

b-cos

B-cos Networks: Alignment is All we Need for Interpretability

baal

Library to enable Bayesian active learning in your research or labeling work.

binary-latent-diffusion

Implementation of Binary Latent Diffusion

bitcoinbook

Mastering Bitcoin 2nd Edition - Programming the Open Blockchain

built-onnxruntime-for-raspberrypi-linux

Built python wheel files of https://github.com/microsoft/onnxruntime for raspberry pi 32bit linux.

chatgpt_please_improve_my_paper_writing

lol

clean-fid

PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)