🛣 Building an end-to-end Promptable Semantic Segmentation (Computer Vision) project from training to inferencing a model on LandCover.ai data (Satellite Imagery).

3クラス(肌、服、髪)のセマンティックセグメンテーションを実施するモデル(A model that performs semantic segmentation of 3 classes(skin, clothes, hair))

Semantic Segmentation on Cityscapes using Segmentation Models Pytorch

A full deep learning pipeline for satellite image semantic segmentation (originally designed for detection of built structures) using Segmentation Models PyTorch.

Segmentation of cancerous tumors using Mamba. Code, resources, and paper provided. We manage to make a small (42k param) model that can segment pretty well.

This repository contains the code to train a custom DGCNN segmentation model on 3D point cloud data and carry out post-processing to filter these point clouds from the k-regular graphs produced by the model.

This repository contains code and results for a semantic segmentation competition using a small autonomous driving dataset. The project explores various data augmentation, network architectures, and training strategies to improve segmentation accuracy and efficiency.

Segmenting the functional tissue units of colon histopathology images.

Bone Age Maturity estimation using a Lateral Cephalogram X-ray image and deep neural networks (UNet)

Deep Hierarchical Semantic Segmentation — Pixel-Wise Classification with Multi-Level Labels

Implementing FCN & U-Net from scratch, then scaling with segmentation_models_pytorch — covering binary and multi-class segmentation on real-world datasets. / FCN, U-Net 논문 직접 구현부터 SMP 라이브러리 활용까지 — 실제 데이터셋으로 이진/다중 클래스 세그멘테이션을 단계적으로 학습한 기록.

A General Tracking Framework for ML-based Time-Symmetric Tracking.

This project offers an easy, flexible, modular PyTorch implementation for semantic segmentation to minimize configuration, automate training and deployment, and enable customization of models, encoders, losses and datasets through its modular design.

The application is designed for editing a car: changing the color of the body, lights, windows and wheels

Development for my M.Tech Thesis: Deep Learning Techniques for Road Segmentation in Indian Context

Dense Prediction Vision Transformer (DPT) - ADE20K Reimplementation

Code accompanying the paper "Comprehensive evaluation of cross-cancer generalization in histopathology segmentation models across 21 tumor types." Includes annotation scripts, segmentation inference, manual scoring app, and statistical analysis.

image segmentation using spiking neural network

Custom deep learning model for 3D medical image segmentation, enhancing the UNETR architecture with lightweight attention gates on its skip connections. This proof-of-concept aimed to improve how the model combines features from different resolution levels. Experiments on MRI scans suggest this could be effective with larger training setups.

collection of methods to cope with the semantic segmentation DL tasks