AminParvaneh/alpha_mix_active_learning
The official implementation of Active Learning by Feature Mixing (ALFA-Mix) paper
This tool helps machine learning practitioners or researchers efficiently train image classification models when they have a large amount of unlabeled image data but limited labeled data. It takes your datasets (like images for classification) and, through 'active learning' strategies, intelligently selects the most informative images to label, saving time and resources. The output is a more accurate image classification model with less labeling effort.
No commits in the last 6 months.
Use this if you need to train an image classifier but have a small budget or limited time for manual data labeling.
Not ideal if you already have a fully labeled dataset and don't need to selectively identify data points for annotation.
Stars
88
Forks
13
Language
Python
License
—
Category
Last pushed
Nov 27, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AminParvaneh/alpha_mix_active_learning"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ntucllab/libact
Pool-based active learning in Python
scikit-activeml/scikit-activeml
scikit-activeml: A Comprehensive and User-friendly Active Learning Library
python-adaptive/adaptive
:chart_with_upwards_trend: Adaptive: parallel active learning of mathematical functions
NUAA-AL/ALiPy
ALiPy: Active Learning in Python is an active learning python toolbox, which allows users to...
ai4co/awesome-fm4co
Recent research papers about Foundation Models for Combinatorial Optimization