dlmacedo/distinction-maximization-loss
A project to improve out-of-distribution detection (open set recognition) and uncertainty estimation by changing a few lines of code in your project! Perform efficient inferences (i.e., do not increase inference time) without repetitive model training, hyperparameter tuning, or collecting additional data.
This project helps machine learning engineers improve the reliability of their image classification models when encountering unfamiliar data. By replacing a standard component in their neural network, they can make their models better at recognizing when an input image doesn't fit any known category, and also provide more trustworthy predictions without slowing down inference.
No commits in the last 6 months.
Use this if you need your image classification models to reliably identify images that fall outside of their training data, or if you require more confident predictions from your models without increasing processing time.
Not ideal if you are looking for a pre-built, ready-to-use application and are not comfortable with modifying Python code for deep learning models.
Stars
44
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Sep 22, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dlmacedo/distinction-maximization-loss"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yzhao062/pyod
A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques
unit8co/darts
A python library for user-friendly forecasting and anomaly detection on time series.
elki-project/elki
ELKI Data Mining Toolkit
raphaelvallat/antropy
AntroPy: entropy and complexity of (EEG) time-series in Python
Minqi824/ADBench
Official Implement of "ADBench: Anomaly Detection Benchmark", NeurIPS 2022.