README.md

TTAC++

This repository is an official implementation for our TPAMI paper [Arxiv] [IEEE Xplore].

This repo is built upon our previous work TTAC accepted by NeurIPS 2022.

Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularizad Self-Training

Yongyi Su¹   Xun Xu²   Tianrui Li³   Kui Jia^1
1South China University of Technology  
²Institute for Infocomm Research, A*STAR  
³Southwest Jiaotong University

Overview

CIFAR10/100

The code is released in the cifar folder.

ImageNet-C

The code is released in the imagenet folder.

Citation

If you find our work useful in your research, please consider citing:

@ARTICLE{su2024revisiting,
  author={Su, Yongyi and Xu, Xun and Li, Tianrui and Jia, Kui},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
  title={Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Training}, 
  year={2024},
  volume={},
  number={},
  pages={1-16},
  doi={10.1109/TPAMI.2024.3370963}
}