Library to recognise and classify faces.
-
Updated
Jul 26, 2021 - Python
Library to recognise and classify faces.
A GPT-based Intent classifier service that can be used to provide inferencing via HTTP with FastAPI
A streamlit web app that allows you to train Few Shot image classification models
LLMs for Low Resource Languages in Multilingual, Multimodal and Dialectal Settings
Code for "Improved Few-Shot Visual Classification"
Non-Euclidean implementations for few-shot image classification on the mini-ImageNet dataset
Automatic Categorization of Software Repository Domains with Minimal Resources
Using Few Shot Learning (FSL) for image classification on Oxford 17 Flowers dataset. Part of HKU COMP3340 Group 10 Project (2023-24 Sem2).
Code for paper the "Distance-Ratio-Based Formulation for Metric Learning"
Supplementary Material For the Paper "NUTS, NARS, and Speech"
Pre-training a Masked Autoencoder with the idea of Diffusion Models for Hyperspectral Image Classification.
NAACL2022 Interactive Symbol Grounding with Complex Referential Expressions
A demonstration repo for how to do automatic translation using local llms.
Code Repository for "SFT: Few-Shot Learning via Self-Supervised Feature Fusion With Transformer"
This repository contains the source code for the IMAML-IDCG (ImageNet Model Agnostic Meta-learning for Invasive Ductal Carcinoma Grading)
Flower Recognition: Dealing with Less Data via Few-Shot Learning
This repository contains the firth bias reduction experiments on the few-shot distribution calibration method conducted in the ICLR 2022 spotlight paper "On the Importance of Firth Bias Reduction in Few-Shot Classification".
Code Release of Exploring Sample Relationship for Few-Shot Classification
Mineral Prediction based on Prototype Learning
Dynamic Few-Shot Prompting is a Python package that dynamically selects N samples that are contextually close to the user's task or query from a knowledge base (similar to RAG) to include in the prompt.
Add a description, image, and links to the few-shot-classifcation topic page so that developers can more easily learn about it.
To associate your repository with the few-shot-classifcation topic, visit your repo's landing page and select "manage topics."