zqiao11/TSCIL
[KDD2024] Class-incremental Learning for Time Series: Benchmark and Evaluation
This project offers a standardized way to evaluate machine learning models that learn continuously from new time series data without forgetting old information. It takes raw or pre-processed real-world time series datasets and produces trained models and performance metrics for various continual learning strategies. Data scientists, machine learning engineers, and researchers working with evolving sensor data, activity recognition, or gesture recognition would find this useful.
No commits in the last 6 months.
Use this if you need to benchmark or develop new class-incremental learning algorithms for time series data, ensuring your models adapt to new data over time while retaining knowledge of previous classes.
Not ideal if you are looking for a pre-trained, production-ready model or if your focus is on traditional, static time series classification without the need for continuous learning.
Stars
65
Forks
11
Language
Python
License
—
Category
Last pushed
Jun 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zqiao11/TSCIL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aimagelab/mammoth
An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of...
LAMDA-CL/PyCIL
PyCIL: A Python Toolbox for Class-Incremental Learning
GMvandeVen/continual-learning
PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR,...
LAMDA-CL/LAMDA-PILOT
🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox
mmasana/FACIL
Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.