Ayaan Haque
Hi! I'm Ayaan Haque, an 18 y/o freshman at UC Berkeley studying Electrical Engineering and Computer Science (EECS).
My research interests are in deep learning (DL) and computer vision (CV). I'm currently working with Prof. Angjoo Kanazawa at BAIR
on NeRFs and generative 3D vision research.
In the past, I've tackled the "limited-labeled data" problem in imaging,
leveraging self-supervised and unsupervised representation learning.
Most recently, I interned at Samsung SDSA where I worked on unsupervised representation
learning for 3D mesh analysis. I got my research career jumpstarted with the Wang Group at Stanfordβs Radiological Sciences Lab,
where I addressed clinical imaging tasks using semi-supervised, self-supervised, and multi-task learning.
While I'm a researcher at heart, I love building π§± and hacking (I'm a MLH Top-50 Hacker!), and I've been exploring startups on the side.
Most importantly, my projects are centered around making an impact in my communities, whether it be locally
or all the way back in Bangladesh. Other than that, I enjoy writing, watching/playing sports, eating out with friends,
and just having a good time. My ongoing goal and dream:
Twitter  / 
Email  / 
Resume  / 
Github  / 
Google Scholar  / 
Medium  / 
LinkedIn
|
Learning about learning π―
|
Research
My research focus is in deep learning, specifically computer vision, and I've published award-winning work in these fields.
I've also conducted research in other fields from NLP and intelligent robotics. Only my relevant papers are listed below. For a full list of my papers,
visit my Google Scholar.
|
|
Self-Supervised Contrastive Representation Learning for 3D Mesh Segmentation
Ayaan Haque,
Hankyu Moon,
Heng Hao,
Sima Didari,
Jae Oh Woo,
Patrick Bangert
Samsung SDS Research America
AAAI Conference on Artificial Intelligence (AAAI), 2023
ArXiv /
Poster /
Twitter Thread /
BibTex
We introduce self-supervised MeshCNN, or SSL-MeshCNN, a novel mesh-specialized contrastive learning method to
perform downstream segmentation with limited-labeled data. We create an augmentation policy tailored for meshes,
enabling the network to learn efficient visual representations through contrastive pre-training.
|
|
Window Level is a Strong Denoising Surrogate
Ayaan Haque1, 2,
Adam Wang2,
Abdullah-Al-Zubaer Imran2
Saratoga High School1, Stanford University2
MICCAI Machine Learning in Medical Imaging (MLMI), 2021 (Poster Presentation w/ 5-Min Oral Presentation)
Project Page /
ArXiv /
Oral /
Poster /
Presentation /
Code /
Blog /
Proceedings /
BibTex
We introduce SSWL-IDN, a novel self-supervised CT denoising window-level prediction surrogate task. Our method is task-relevant
and related to the downstream task, yielding improved performance over recent methods.
|
|
MultiMix: Sparingly Supervised, Extreme Multitask Learning From Medical Images
Ayaan Haque1,
Abdullah-Al-Zubaer Imran2,3,
Adam Wang2,
Demetri Terzopoulos3,4
Saratoga High School1, Stanford University2, University of California, Los Angeles3, VoxelCloud Inc.4
IEEE International Symposium on Biomedical Imaging (ISBI), 2021 (Oral Audio and Poster Presentation)
Project Page /
ArXiv /
Oral /
Poster /
Presentation /
Code /
Blog /
Proceedings /
BibTex
We introduce MultiMix, a joint semi-supervised classification and segmentation model
employing a confidence-based augmentation strategy for semi-supervised classification
along with a novel saliency bridge module that guides segmentation and provides explainability
for the joint tasks.
|
|
EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs
Ayaan Haque
Saratoga High School
AAAI Conference on Artificial Intelligence (AAAI), 2021 (Best Student Abstract Finalist, Oral and Poster Presentation)
Project Page /
ArXiv /
Oral /
Poster /
Presentation /
Code /
Blog /
Proceedings /
BibTex
We propose EC-GAN, which combines a Generative Adversarial Network with a classifier to leverage artifical GAN
generations to increase the size of restricted, fully-supervised datasets using semi-supervised algorithms.
Mentored by Microsoft Postdoc and Princeton University PhD Jordan T. Ash.
|
|
Generalized Multi-Task Learning from Substantially Unlabeled Multi-Source Medical Image Data
Ayaan Haque1, 2,
Abdullah-Al-Zubaer Imran2,3,
Adam Wang2,
Demetri Terzopoulos3,4
Saratoga High School1, Stanford University2, University of California, Los Angeles3, VoxelCloud Inc.4
The Journal of Machine Learning for Biomedical Imaging (MELBA), 2021 (Journal Paper)
Project Page /
Journal Page /
Paper /
Code /
BibTex
We expand upon MultiMix (in ISBI 2021). Our extended manuscript contains a detailed
explanation of the methods, saliency map visualizations from multiple datasets, and
quantitative (performance metrics tables) and qualitative (mask predictions, Bland
Altman plots, ROC curves, consistency plots).
|
|
Noise2Quality: Non-Reference, Pixel-Wise Assessment of Low Dose CT Image Quality
Ayaan Haque1, 2,
Adam Wang2,
Abdullah-Al-Zubaer Imran2
Saratoga High School1, Stanford University2
SPIE Medical Imaging (SPIE), 2022 (Poster Presentation)
Project Page /
Paper /
Presentation /
Poster /
Code /
BibTex
We propose Noise2Quality (N2Q), a novel, self-supervised IQA model which predicts SSIM Image Quality maps from
low-dose CT. We propose a self-supervised regularization task of dose-level estimation creating a
multi-tasking framework to improve performance.
|
|
Deep Learning for Suicide and Depression Identification with Unsupervised Label Correction
Ayaan Haque1,
Viraaj Reddi1,
Tyler Giallanza2
Saratoga High School1, Princeton University2
International Conference on Artificial Neural Networks (ICANN), 2021 (Poster Presentation)
Project Page /
ArXiv /
Teaser Video /
Poster /
Code /
Application (SuiSense) /
Blog /
Proceedings /
BibTex
We propose SDCNL to address the unexplored problem of classifying between depression and more severe suicidal
tendencies using web-scraped data. Our method introduces a novel label correction
method to remove inherent noise in web-scraped data using unsupervised learning combined with a deep-learning classifier
based on pre-trained transformers.
|
|
3N-GAN: Semi-Supervised Classification of X-Ray Images with a 3-Player Adversarial Framework
Shafin Haque,
Ayaan Haque
Saratoga High School
ArXiv, 2021
ArXiv /
Code /
BibTex
We propose 3N-GAN, or 3 Network Generative Adversarial Networks, to perform semi-supervised
classification of medical images in fully-supervised settings. We incorporate a classifier
into the adversarial relationship such that the generator trains adversarially against both
the classifier and discriminator. (Authors contributed equally)
|
|
Convolutional Nets for Diabetic Retinopathy Screening in Bangladeshi Patients
Ayaan Haque1,2
Ipsita Sutradhar2,
Mahziba Rahman2,
Mehedi Hasan2,
Malabika Sarker2
Saratoga High School1,
BRAC University School of Public Health2
ArXiv, 2021
ArXiv /
Code /
CAD Designs /
Application (Drishti) /
BibTex
This paper presents specifications on the deep learning model implemented in Drishti. The paper outlines the process
of performing deep learning classication of diabetic retinopathy and contains extensive evaluation of the method
on real fundus images collected from the Bangladesh Eye Hospital and BRAC University.
|
|
Simulated Data Generation Through Algorithmic Force Coefficient Estimation for AI-Based Robotic Projectile Launch Modeling
Sajiv Shah1,
Ayaan Haque1,
Fei Liu2
Saratoga High School1, University of California, San Diego2
IEEE Asia-Pacific Conference on Intelligent Robot Systems (ACIRS), 2021 (Best Presentation, Oral and Poster Presentation)
Project Page /
ArXiv /
Oral /
Presentation /
Poster /
Code /
Blog /
Proceedings /
BibTex
We propose FCE-NN, a novel method of modeling robotic launching of non-rigid objects using neural networks which are trained
with supplemental simulated data, generated from algorithmic force coefficient estimation. (Authors contributed equally, order arbitrarily assigned)
|
Experience
I've held various positions at companies and
universities, a few of which are listed here. I primarily work on research problems, but I also have experience in traditional software engineering.
|
|
Research Intern at Berkeley AI Research (BAIR)
Kanazawa AI Lab (KAIR) @ BAIR, Berkeley, CA
Dec 2022 - Present
- Working on NeRFs and diffusion models
|
|
AI Research Intern at Samsung SDSA
AI Research Group @ Samsung SDSA, San Jose, CA
June 2022 - September 2022
- Proposed "SSL-MeshCNN", a novel self-supervised algorithm for segmenting non-uniform, irregular 3D meshes
- Introduced new SimCLR-inspired stochastic augmentation policy for mesh-specialized contrastive learning
- Matched accuracy of fully-supervised training (90.50%) with just 67% of labels on benchmark datasets
- Wrote paper accepted to AAAI 2023, available on ArXiv
|
|
AI Research Intern at Stanford
Wang Group in RSL @ Stanford, Stanford, CA
July 2020 - June 2022
- Worked on learning from limited labeled data for clinical imaging tasks using unsupervised, self-supervised, and semi-supervised techniques
- Developed research skills by running hundreds of experiments, writing papers, preparing supplementals, and writing rebuttals
|
|
Software Engineering Intern at Openwater Accelerator
Internal SWE Team @ Openwater VC Accelerator, Menlo Park, CA
August 2020 - December 2020
- Developing a Waitlist API which is to be sold to porfolio companies in the program, where companies can establish
waitlists for their products to build a market
- Using React.js, MongoDB, Flask and other web dev/backend tech, integrating Stripe payment features and referral features, writing documentation
- Recruited by CEO David Bromberg and assigned to developing waitlist product, under contract with payment
through equity ownership of product
|
|
Content Writer for Towards Data Science
Medium
June 2020 - Present
- Writer on Medium for multiple publications: Towards Data Science (Primary, 577k, top publication), Better Programming
(154k), Codeburst (100k), TowardsAI (22k), and more
- 4x Editorβs Pick on TDS, chosen for Hands on Tutorial and Thoughts and Theory Column, Featured on Medium home page twice, 21.6k+ total
views, 3800+ likes
- Wrote articles about AI/CS topics, activities and projects, and tips and advice
|
Activities
Outside of research, I enjoy building practical applications in both competitive and casual formats.
|
|
Hackathons
Team Captain
May 2019 - Present
- Team Captain of 5 total members (shoutout Viraaj, Adithya, Ishaan, and Sajiv)
- Created numerous projects (listed in Projects section)
- π 33x Award Winner, 9x First Place, 22x Top 3, $10,000+ in earnings
- Chosen for MLH Top 50 Hackers Class of 2021, one of five high schoolers
|
|
MSET Robotics Team 649
Software Team
August 2018 - April 2021
- FRC Robotics Software Team, ML-Specialist (FTC Captain 9th Grade)
- Worked with AI/ML for in-game object detection and using predictive models for shot selection, work on shooter
trajectory modeling, write documentation
- π 2021 Skills Competition Finalist in Carbon Group π 2021 Engineering Excellence Award π CalGames 2019 Finalist π ChezyChamps 2019 Semi-Finalist
|
Projects
I've just listed a few of my many projects, and the remaining are available on my Github. On Github, I have 500+ commits and ~300 stars across all my repositories.
Check out this cool commit graph, and check this out for my Github stats.
|
|
SuiSense
Using Artificial Intelligence to distinguish between suicidal and depressive messages
June 2020 - Dec 2020
Website /
Demo /
Github /
Devpost /
Medium Article /
Research Paper (SDCNL)
SuiSense is a progressive web application that uses Artificial Intelligence (AI) and Natural Language Processing
(NLP) to distinguish between depressive and suicidal phrases and help concerned friends and family determine whether
their struggling loved one is on the path to suicide. SuiSense uses an implementation of SDCNL.
π 4th Place Congressional App Challenge 2020 π 2nd Place @ GeomHacks 2020 π HM @ MLH Summer League SHDH 2020
In order to continue expanding our project and implementing it, we are currently working with two therapists, Dr. Paul Marcille
and Dr. Marilee Ruebsamen, who act as our advisors and consultants. With their help, we have begun an implementation process in our local community.
Stack: Python, HTML, CSS, JavaScript, Tensorflow, PyTorch, BERT, Flask, PythonAnywhere, Pandas, Sci-Kit Learn
|
|
Drishti Smartphone Retinal Camera System
CAD Files and Implementation Drishti's Retinal Camera System Prototype
June 2021 - Sep 2021
Github (CAD Files) /
Assembly Guide /
Instructional Guide /
Documentation /
Technical Blog /
Drishti Website
This mobile, on-the-go system is designed for clinics in Bangladesh to screen patients for
Diabetic Retinopathy (DR) using a smartphone camera with a retinal attachment. The purpose
of this rig is to allow precise positioning of the smartphone to any patient's left and right
eye such that the images can be efficiently fed into Drishti's AI algorithms for DR diagnosis.
The system is completely adjustable for all head sizes. It is made of readily available
components that can be purchased at many local hardware stores, and is designed for low-cost
fabrication. All assembly tools are common household tools or easily purchasable/rentable
from a local hardware store. The 3D-printed components can be printed on low-end machines
and with cheap PLA filament. We designed this system to be completely collapsable, such that
it can fit into a standard size backpack.
Stack: SolidWorks, Hardware Materials
|
|
Tickbird
Streamlined prescription analysis for visually impaired patients (Available on the App Store)
September 2019 - June 2020
Website /
App Store /
Demo /
Github /
Slides /
Devpost /
Saratoga Falcon Article /
Landing Page Code
Tickbird is an advanced Swift mobile app based on the TesseractOCR neural network framework allowing visually impaired patients
to aurally understand their prescriptions or the labels on their pill bottles in order to gain independence and avoid
the prospect of lethal miscommunication regarding necessary medicines from their doctors. Moreover, the app's smart
profiling feature not only finds the nearest pharmacy containing the user's prescription, but it also uses AI/ML
algorithms to detect and set notifications for the times the user has to take or refill their medicine.
π 2x Award Winner @ OmniHacks 2019 π App Store April 2020, 1000+ Impresions
Stack: Swift, Xcode, IOS, Firebase, TesseractOCR, Ruby
|
|
TecConnect
Connecting schools to donate or request devices to aid COVID Learning
April 2020 - June 2020
Website /
Demo /
Github /
Proposal /
Executive Summary /
Devpost /
Medium Article
TecConnect is a unique PWA that allows impoverished and wealthy schools to easily connect and transfer devices
from those who have them to ones who donβt. Due to the COVID crisis, low-income students don't have access to
devices, and as a result, are falling behind in their education. However, many schools have surpluses of devices
that are currently being wasted.Thus, we developed TecConnect to allow struggling schools to request devices from
schools with excess devices. We developed an application specifically for schools and the state government. We plan
to implement our software as part of a statewide plan to promote device sharing in all schools.
π 1st Place Grand Prize Winner @ AI4ALL CreAItivity Challenge 2020
π 1st Place Grand Prize Winner @ Saratoga Congressional Hackathon 2020
π Sponsor Prize Winner @ MLH Summer League RH 2020
Stack: HTML, Javascript, CSS, Firebase, MongoDB, Radar.io, Google Cloud
|
|
PreDent
Using ML to promote safer driving by predicting crash hotspots
June 2020
Website /
Demo /
Github /
Devpost /
Documentation
PreDent is a unique progressive web application that identifies the accident-prone areas of a city through machine
learning. The core of our project is an ML model that inputs static features (speed limits, road signs, road
curvature, traffic volume), weather (precipitation, temperature), human factors, and many other attributes to
ultimately output a map of city roads with hotspots of where collisions are likely.
π 1st Place Overall @ MLH Summer League Data Day Grind 2020
π 1st Place Overall, Best Web Application π Sponsored Prize Winner @ MacroHacks 2020
π 2nd Place Overall @ PlatHacks 2020
π 3rd Place Overall @ HackMann 2020
Stack: Python, HTML, Javascript, CSS, Keras, GeoPandas, Sci-Kit Learn, UIPath, Google Cloud
|
Awards, Honors, and Achievements
A brief summary of my relevant awards, honors, and achievements.
|
AAAI Best Student Abstract Finalist 2021
Chosen as a finalist for best student papers for my EC-GAN paper at AAAI 2021 (Top-5 Overall CS Conference/Publication), only high schooler in 35 year history
to be selected, 20 of the 105 qualifying papers selected as finalists, chosen for oral 3-minute thesis presentation
|
Major League Hacking Top 50 Hacker 2021
Chosen for Major League Hacking (MLH) Top 50 Hacker, which recognizes the most successful and
impactful hackers in a community of 500,000 hackers. One of 5 high schoolers, chosen,
second youngest chosen. Highlighted in public profile.
|
4th Place Congressional App Challenge
Awarded 4th place for the Congressional App Challenge for our project SuiSense, a national programming challenge
held by US Congress, received hand-written letter from Congresswomen Anna Eshoo
|
ACIRS Best Presentation Award 2021
Selected as Best Presentation Award for our FCE-NN
presentation at
ACIRS 2021 (Top Robotics Conference/Publication), only high schoolers in history
to be selected
|
33x Hackathon Winner
Accumulated 33 hackathon awards for various projects, amongst the highest wins in history. Full list of projects available on Devpost
|
Writing
I write on Medium (semi-regularly) to share my thoughts with the world. Here are a few of my favorite medium articles that I have written.
|
|
In Response to βWhatβs the F-ing Point?β
No Publication, will not profit off this story
October 6th, 2021
A response to an article discussing our purpose in this world combined with a discussion of my own purpose
This article is a reponse to my friend's article, where
he discusses critiques of our Saratoga society. In my article, I respond to his ideas and then share my own story of finding my purpose in life.
|
|
Burnout β The Bane of Progress
Towards Data Science
April 4th, 2021
How being an AI developer, hacker, and researcher lead to some of my lowest moments
This is a personal narrative and reflection on how I have learned to cope
through draining times as an AI developer.
|
|
How Five High-Schoolers Won $9.5K From Hackathons in One Summer
Better Programming
August 28th, 2020
Coding, winning prizes, and proving ourselves
Authored by Ayaan Haque, Adithya Peruvemba, Viraaj Reddi, Sajiv Shah, and Ishaan Bhandari
This article travels through the journey of my team, Haleakala Hacksquad, and how we became great hackers.
|
Community Service
With my technical skills, I love contributing to my community and learning the stories of those I support. Whether
these are my local communities or my home country Bangladesh, I always build strong relationships with those I serve.
|
|
Drishti
Founder
November 2019 - Present
Website /
Video Guide /
Github Organization /
Paper /
CNN Code /
Smartphone System Design
Drishti is an organization with an AI algorithm that screens Bangladeshi patients for diabetic retinopathy (DR).
Our mission is to provide free, accessible early screening to areas where DR specialists are
not available. With academic, clinical, and organizational support, we are able to widen the
reach of our service. We are partnered with BRAC University and have published a validation study on the algorithm,
achieving high accuracy on Bangladeshi eyes. In addition, we have developed a novel
smartphone retinal camera system (patent application in process) which will be integrated into our clinics.
|
|
Jaago Robotics
Founder
May 2018 - Present
Website
Jaago Robotics is an organization partnered with the Jaago Foundation to teach robotics and coding to students at the Jaago School (a tuition free institute). As a branch of the Jaago Foundation, we use the Lego Mindstorms EV3
Robotics kit to help young students learn introductory robotics concepts, providing new opportunities for bright students. We go once every year and have gone twice
so far (in the summer of 2018 and winter of 2019) and have taught over 20+ students.
I founded Jaago Robotics with my brother the summer of 2018, as a rising freshman. We have achieved so much with the students,
most notably when the students presented their work to sponsors from Levi Strauss to receive funding for their school.
We plan to return in December of 2021 to work with even more students.
|
|