Shafin Haque

Hi! I'm Shafin, a rising freshman at UC Berkeley studying Electrical Engineering and Computer Sciences (EECS).

I'm interested in machine learning and computer vision. Currently, I'm working for Invisible AI as a computer vision intern where I'm building deep learning systems for manufacturing.

Previously, I was researching novel object detection methods on marine data for the Vision Research Lab at UC Santa Barbara.

Email  /  Resume  /  LinkedIn  /  Google Scholar  /  Github  /  Devpost

profile photo

My research primarly focuses on computer vision, but I have also worked in other deep learning fields.

Box Prediction Rebalancing for Training Single-Stage Object Detectors with Partially Labeled Data
Shafin Haque, R. Austin McEver
NeurIPS Workshop (NeurIPS LMRL), 2022
Paper  / Poster

We propose Box Prediction Rebalancing for single-stage object detectors to combat the challenge of learning from partially annotated datasets. By randomly removing percentages of negative predictions from our model's loss computation, our model performs better as it learns less from false positives which may be true species of interest without ground truth.

CCTV Latent Representations for Reducing Accident Response Times
Shafin Haque
ACM International Conference on Computer Graphics and Virtuality (ICCGV), 2022
Paper / Code / Proceedings

We introduce a novel dataset for detecting car accidents and unusual street activity through live CCTV cameras. We annotate the videos with metadata to help with future trend prediction, as well as give more information for each video. We also propose a deep learning system to cluster similar activity based on latent space representations.

3N-GAN: Semi-Supervised Classification of X-Ray Images with a 3- Adversarial Frame
Shafin Haque*, Ayaan Haque
Preprint on ArXiv, 2021
Paper / Code

We propose a novel GAN structure for semi-supervised classification of medical images in restricted, fully supervised data. We incorporate a classifier into the adversarial relationship such that the generator trains adversarially against both the classifier and discriminator.

Improving Clinical Efficiency and Reducing Medical Errors through NLP-enabled diagnosis of Health Conditions from Transcription Reports
Krish Maniar*, Shafin Haque*, Kabir Ramzan*
Volume 8, Issue 3 of International Journal of Scientific Research (IJSRCSEIT), 2022
Paper / Code / Proceedings

In an effort to streamline the process for medical practitioners and improve clinical care for patients within the hospital we introduce a machine learning based NLP approach for classifying healthcare conditions from transcription notes.


I have been fortunate enough to work for both companies and universities solving machine learning problems.

Computer Vision Intern at Invisible AI February 2023 - Present
Invisible AI
  • Developing deep learning models for manufacturing processes.
Computer Vision Research Intern at UCSB March 2022 - December 2022
Vision Research Lab
  • Worked with marine scientist group to develop dataset for streamlining identification and counting process of marine species in underwater ROV videos.
  • Wrote extended abstract accepted to NeurIPS LMRL proposing novel box rebalancing method for single-stage object detectors to improve learning from partially labeled datasets. Also contributed to paper accepted to CVPR Workshop and The International Journal of Computer Vision.
Research Assistant at Stanford December 2021 - March 2022
Quanitative Imaging and Artificial Intelligence Lab
  • Researched the application of federated learning in medical imaging in order to improve security and accuracy of 2D and 3D segmentation of multi-organ and tumor abdominal CT scans.
Machine Learning Intern at Tech for Good Inc June 2021 - December 2021
Computer Vision Section Lead
  • Programmed deep learning models in TensorFlow and PyTorch to detect distracted/impaired drivers in images and video.
  • Used custom and pre-trained CNNs to reach an accuracy of 99% for distinguishing between multiple classes of distracted and non distracted driving. Also tested with CNN-RNN architecture for video classification.
  • Lead computer vision team on the project by overseeing all team operations and holding meetings. Lead collaboration with software engineering team to develop mobile application using Flutter.

I've competed in numerous hackathons and these are some of the projects created during them. There are also some personal projects listed and more of my projects can be found on my Github or Devpost.

Python, TensorFlow, Flask, HTML/CSS/JS
Website / Code / Devpost / Demo
  • Python web app for prediction various characteristics of wildfires with ML. Used neural networks, regression, and bounding box detection models
  • 4th place Congressional App Challenge 2021 & 4x Hackaton Award Winner
Pitch Prediction
R, Python, RShiny, TensorFlow, Caret
RShiny App / Code / Medium Article
  • RShiny app for predicting the next pitch in baseball based on current game scenario with R and Python
  • Wrote article published in TowardsAI documenting process
Python, TensorFlow, Flask, Firebase, HTML/CSS/JS
Code / Devpost / Demo
  • Flask app for detecting eye disorders and effects of treatment with Firebase backend
  • 4x hackathon award winner
Vue.JS, TensorFlow.js, AutoML, Firebase
Website / Code / Devpost / Demo
  • Vue.JS app with TensoFlow.js and AutoML for detecting and classifying COVID-19 and the flu with Firebase backend
  • Google sponsor prize winner
Python, TensorFlow, Flask, HTML/CSS/JS
Code / Devpost / Demo
  • Web app for detecting and predicting various characteristics of different natural disasters
  • 6x hackathon award winner

Website template from here