Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/Gorilla-Lab-SCUT/TTAC

[NeurIPS 2022] Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering
https://github.com/Gorilla-Lab-SCUT/TTAC

deep-learning domain-adaptation pseudo-labeling test-time-adaptation test-time-training

Last synced: about 2 months ago
JSON representation

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

Awesome Lists containing this project

README

        

# TTAC

This repository is an official implementation for our NeurIPS 2022 paper [\[Arxiv\]](https://arxiv.org/abs/2206.02721) [\[Openreview\]](https://openreview.net/forum?id=W-_4hgRkwb).

We implement a plug and play version of TTAC without queue on another work [repo](https://github.com/Gorilla-Lab-SCUT/TRIBE/blob/master/core/adapter/ttac.py).

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

**Yongyi Su1**   **Xun Xu21**   **Kui Jia13**


1South China University of Technology   2Institute for Infocomm Research   3Peng Cheng Laboratory

### Overview

![](./imgs/Overview_v1.png)

### CIFAR10/100

The code is released in the [cifar](cifar) folder.

### ImageNet-C

The code is released in the [imagenet](imagenet) folder.

### Citation

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

```bibtex
@inproceedings{
su2022revisiting,
title={Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering},
author={Yongyi Su and Xun Xu and Kui Jia},
booktitle={Advances in Neural Information Processing Systems},
editor={Alice H. Oh and Alekh Agarwal and Danielle Belgrave and Kyunghyun Cho},
year={2022},
url={https://openreview.net/forum?id=W-_4hgRkwb}
}
```