Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yushu, Su, Yongyi, Yang, Xulei, Jia, Kui, Xu, Xun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910760534278144
author Li, Yushu
Su, Yongyi
Yang, Xulei
Jia, Kui
Xu, Xun
author_facet Li, Yushu
Su, Yongyi
Yang, Xulei
Jia, Kui
Xu, Xun
contents Existing test-time adaptation (TTA) approaches often adapt models with the unlabeled testing data stream. A recent attempt relaxed the assumption by introducing limited human annotation, referred to as Human-In-the-Loop Test-Time Adaptation (HILTTA) in this study. The focus of existing HILTTA studies lies in selecting the most informative samples to label, a.k.a. active learning. In this work, we are motivated by a pitfall of TTA, i.e. sensitivity to hyper-parameters, and propose to approach HILTTA by synergizing active learning and model selection. Specifically, we first select samples for human annotation (active learning) and then use the labeled data to select optimal hyper-parameters (model selection). To prevent the model selection process from overfitting to local distributions, multiple regularization techniques are employed to complement the validation objective. A sample selection strategy is further tailored by considering the balance between active learning and model selection purposes. We demonstrate on 5 TTA datasets that the proposed HILTTA approach is compatible with off-the-shelf TTA methods and such combinations substantially outperform the state-of-the-art HILTTA methods. Importantly, our proposed method can always prevent choosing the worst hyper-parameters on all off-the-shelf TTA methods. The source code is available at https://github.com/Yushu-Li/HILTTA.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18911
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection
Li, Yushu
Su, Yongyi
Yang, Xulei
Jia, Kui
Xu, Xun
Computer Vision and Pattern Recognition
Existing test-time adaptation (TTA) approaches often adapt models with the unlabeled testing data stream. A recent attempt relaxed the assumption by introducing limited human annotation, referred to as Human-In-the-Loop Test-Time Adaptation (HILTTA) in this study. The focus of existing HILTTA studies lies in selecting the most informative samples to label, a.k.a. active learning. In this work, we are motivated by a pitfall of TTA, i.e. sensitivity to hyper-parameters, and propose to approach HILTTA by synergizing active learning and model selection. Specifically, we first select samples for human annotation (active learning) and then use the labeled data to select optimal hyper-parameters (model selection). To prevent the model selection process from overfitting to local distributions, multiple regularization techniques are employed to complement the validation objective. A sample selection strategy is further tailored by considering the balance between active learning and model selection purposes. We demonstrate on 5 TTA datasets that the proposed HILTTA approach is compatible with off-the-shelf TTA methods and such combinations substantially outperform the state-of-the-art HILTTA methods. Importantly, our proposed method can always prevent choosing the worst hyper-parameters on all off-the-shelf TTA methods. The source code is available at https://github.com/Yushu-Li/HILTTA.
title Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.18911