Test-time Adaptation

120 papers with code • 1 benchmarks • 1 datasets

This task has no description! Would you like to contribute one?


Use these libraries to find Test-time Adaptation models and implementations


Most implemented papers

Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions

jiachens/ModelNet40-C 28 Jan 2022

Deep neural networks on 3D point cloud data have been widely used in the real world, especially in safety-critical applications.

Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation

neerakara/test-time-adaptable-neural-networks-for-domain-generalization 9 Apr 2020

In medical image segmentation, this premise is violated when there is a mismatch between training and test images in terms of their acquisition details, such as the scanner model or the protocol.

Tent: Fully Test-time Adaptation by Entropy Minimization

DequanWang/tent ICLR 2021

A model must adapt itself to generalize to new and different data during testing.

MEMO: Test Time Robustness via Adaptation and Augmentation

zhangmarvin/memo 18 Oct 2021

We study the problem of test time robustification, i. e., using the test input to improve model robustness.

Continual Test-Time Domain Adaptation

qinenergy/cotta CVPR 2022

However, real-world machine perception systems are running in non-stationary and continually changing environments where the target domain distribution can change over time.

Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition

daniellin94144/test-time-adaptation-asr-suta 27 Mar 2022

Although deep learning-based end-to-end Automatic Speech Recognition (ASR) has shown remarkable performance in recent years, it suffers severe performance regression on test samples drawn from different data distributions.

Test-Time Adaptation via Self-Training with Nearest Neighbor Information

mingukjang/tast 8 Jul 2022

To overcome this limitation, we propose a novel test-time adaptation method, called Test-time Adaptation via Self-Training with nearest neighbor information (TAST), which is composed of the following procedures: (1) adds trainable adaptation modules on top of the trained feature extractor; (2) newly defines a pseudo-label distribution for the test data by using the nearest neighbor information; (3) trains these modules only a few times during test time to match the nearest neighbor-based pseudo label distribution and a prototype-based class distribution for the test data; and (4) predicts the label of test data using the average predicted class distribution from these modules.

MECTA: Memory-Economic Continual Test-Time Model Adaptation

sonyai/mecta ICLR 2023

The proposed MECTA is efficient and can be seamlessly plugged into state-of-theart CTA algorithms at negligible overhead on computation and memory.

Test Time Adaptation for Blind Image Quality Assessment

subhadeeproy2000/tta-iqa ICCV 2023

In this work, we introduce two novel quality-relevant auxiliary tasks at the batch and sample levels to enable TTA for blind IQA.

Rethinking Class-incremental Learning in the Era of Large Pre-trained Models via Test-Time Adaptation

iemprog/ttacil 17 Oct 2023

However, repeated fine-tuning on each task destroys the rich representations of the PTMs and further leads to forgetting previous tasks.