Popular GitHub Repositories for Normalized Cuts

Image segmentation - general superpixel segmentation & center detection & region growing

(CVPR 2022) Pytorch implementation of "Self-supervised transformers for unsupervised object discovery using normalized cut"

Official code for "A Normalized Gaussian Wasserstein Distance for Tiny Object Detection"

R package providing annotators and a normalized data model for natural language processing

Pytorch implementation of "TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut"

Unofficial Pytorch implementation of SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speaker text-to-speech

This clustering based anomaly detection project implements unsupervised clustering algorithms on the NSL-KDD and IDS 2017 datasets

Automatically generates TTS dataset using audio and associated text. Make cuts under a custom length. Uses Google Speech to text API to perform diarization and transcription or aeneas to force align text to audio.

Official code for "DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut", NeurIPS 2024

A Named Entity Recognition + Entity Linker + Relation Extraction Pipeline built using spacy v3. Given a text, the pipeline will extract entities from the text as trained and will disambiguate the entities to its normalized form through an Entity Linker connected to a Knowledge Base and will assign a relation between the entities, if any.

[MICCAI 2024] CUTS: A Deep Learning and Topological Framework for Multigranular Unsupervised Medical Image Segmentation

The proposed system will be able to predict the crop yield production which will be useful to farmers for harvesting and storage. The system will use the weather forecasting which includes the parameters like temperature, rainfall, humidity, dew point and the normalized difference vegetation index time series from Sentinel-2 satellite for selected region. By using both the results obtained,accurate crop yield prediction can be calculated which will help farmers in planning efficiently, minimize costs and maximize yields—and profits—as a result.

Implementing the MST Research Paper in PyTorch

Official implementation of the paper "AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D Scans"

A (nicer) tokenizer you want to use for model inference and training: with all known peventable gotchas normalized or auto-fixed.

This work proposes a hierarchically normalized physics-informed neural network (hnPINN) to solve PDE problems.

HighNoon LLM uses Hierarchical Spatial Neural Memory (HSMN) to process language like humans, organizing text into a tree for efficiency. It cuts computing needs by 78x, excelling in summarization, coding, and Q&A, while running locally for privacy.

Implementaion of Dynamically Normalized Physics-Informed Neural Networks in TensorFlow

Time Series Analyses and Machine Learning for Classifying Events prior to Fiber Cuts

This project focuses on the prediction of lung cancer using multiple machine learning models and comparing their performances. The dataset used for this project consists of various features related to lung cancer, which were preprocessed, normalized, and then used for training different classifiers.