Next-Gen Neural Networks
Neural Networks Ongoing
This is an on-going project and has closed access before publication.
Pytorch LNN MHN
Research & Projects
A curated list of things I’ve built, tested, and obsessed over.
OOD Segmentation
Segmentation Ongoing
This is an on-going project and has closed access before publication.
Pytorch Nuclei xNN
Cell Nuclei Segmentation
Segmentation Ongoing
This is an on-going project and has closed access before publication.
Pytorch Nuclei SAM
Allergic Rhinitis
Segmentation Completed
Allergic rhinitis diagnosis from nasal endoscopic images.
TensorFlow CNNs Transfer Learning Medical Imaging
Alloy Steel Microstructure
Segmentation Completed
Deep learning segmentation of alloy steel microstructures from SEM images under extreme data and texture ambiguity.
PyTorch Deep Learning SEM Imaging Texture Segmentation
Pipe Defect Detection
Detection Completed
Problem Internal inspection of rocket engine pipes requires reliable detection of surface defects under challenging conditions, including cylindrical geometr...
Pytorch SAM Finetuning
ClimaX via Radar
Generation Completed
Regional radar-based rainfall forecasting using the ClimaX transformer with multi-variable radar inputs.
Pytorch ClimaX Radar
Temperature Super Resolution
Generation Completed
Learning-based super resolution of thermal images to reconstruct high-resolution temperature fields from low-resolution sensor data.
Pytorch UNet
Battery Particle Segmentation
Segmentation Completed
Adapting foundation segmentation models to dense, non-describable particle imagery using semi-automatic labeling and parameter-efficient fine-tuning.
Pytorch SAM Finetuning
Early Fire Detection
Classification Completed
Patch-based fire detection system combining classical vision and deep learning for fast, robust early-stage fire localization on edge devices.
Pytorch YOLO GMM
Screen Panel Anomaly
Detection Completed
Automated detection of subtle surface anomalies on industrial display panels using structured illumination and deep learning.
Pytorch YOLO SAM