Gorilla-Lab-SCUT/TTAC

[NeurIPS 2022] Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering

33
/ 100
Emerging

This project helps machine learning researchers evaluate and improve the robustness of their image classification models. It takes pre-trained image classification models and various image datasets with corruptions as input, providing insights into how well models adapt to unseen, degraded data during inference. Machine learning scientists and deep learning engineers focused on model generalization and reliability would find this useful.

No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner who needs to test and improve the performance of your image classification models on real-world, corrupted, or out-of-distribution images.

Not ideal if you are looking for a general-purpose image labeling tool or a solution for training models from scratch.

model-robustness image-classification deep-learning-research computer-vision model-adaptation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

49

Forks

4

Language

Python

License

MIT

Last pushed

Oct 06, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Gorilla-Lab-SCUT/TTAC"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.