Robust Test-Time Adaptation in Dynamic Scenarios
- URL: http://arxiv.org/abs/2303.13899v1
- Date: Fri, 24 Mar 2023 10:19:14 GMT
- Title: Robust Test-Time Adaptation in Dynamic Scenarios
- Authors: Longhui Yuan, Binhui Xie, Shuang Li
- Abstract summary: Test-time adaptation (TTA) intends to adapt the pretrained model to test distributions with only unlabeled test data streams.
We elaborate a Robust Test-Time Adaptation (RoTTA) method against the complex data stream in PTTA.
Our method is easy to implement, making it a good choice for rapid deployment.
- Score: 9.475271284789969
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Test-time adaptation (TTA) intends to adapt the pretrained model to test
distributions with only unlabeled test data streams. Most of the previous TTA
methods have achieved great success on simple test data streams such as
independently sampled data from single or multiple distributions. However,
these attempts may fail in dynamic scenarios of real-world applications like
autonomous driving, where the environments gradually change and the test data
is sampled correlatively over time. In this work, we explore such practical
test data streams to deploy the model on the fly, namely practical test-time
adaptation (PTTA). To do so, we elaborate a Robust Test-Time Adaptation (RoTTA)
method against the complex data stream in PTTA. More specifically, we present a
robust batch normalization scheme to estimate the normalization statistics.
Meanwhile, a memory bank is utilized to sample category-balanced data with
consideration of timeliness and uncertainty. Further, to stabilize the training
procedure, we develop a time-aware reweighting strategy with a teacher-student
model. Extensive experiments prove that RoTTA enables continual testtime
adaptation on the correlatively sampled data streams. Our method is easy to
implement, making it a good choice for rapid deployment. The code is publicly
available at https://github.com/BIT-DA/RoTTA
Related papers
- Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams [19.921480334048756]
Test-Time Adaptation (TTA) enables adaptation and inference in test data streams with domain shifts from the source.
We propose a novel Distribution Alignment loss for TTA.
We surpass existing methods in non-i.i.d. scenarios and maintain competitive performance under the ideal i.i.d. assumption.
arXiv Detail & Related papers (2024-07-16T19:33:23Z) - Diversity-aware Buffer for Coping with Temporally Correlated Data
Streams in Online Test-time Adaptation [3.1265626879839923]
Test data streams are not always independent and identically distributed (i.i.d.)
We propose a diversity-aware and category-balanced buffer that can simulate an i.i.d. data stream, even in non-i.i.d. scenarios.
We achieve state-of-the-art results on most considered benchmarks.
arXiv Detail & Related papers (2024-01-02T01:56:25Z) - Generalized Robust Test-Time Adaptation in Continuous Dynamic Scenarios [18.527640606971563]
Test-time adaptation (TTA) adapts pre-trained models to test distributions during the inference phase exclusively employing unlabeled test data streams.
We propose a Generalized Robust Test-Time Adaptation (GRoTTA) method to effectively address the difficult problem.
arXiv Detail & Related papers (2023-10-07T07:13:49Z) - A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts [143.14128737978342]
Test-time adaptation, an emerging paradigm, has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions.
Recent progress in this paradigm highlights the significant benefits of utilizing unlabeled data for training self-adapted models prior to inference.
arXiv Detail & Related papers (2023-03-27T16:32:21Z) - DELTA: degradation-free fully test-time adaptation [59.74287982885375]
We find that two unfavorable defects are concealed in the prevalent adaptation methodologies like test-time batch normalization (BN) and self-learning.
First, we reveal that the normalization statistics in test-time BN are completely affected by the currently received test samples, resulting in inaccurate estimates.
Second, we show that during test-time adaptation, the parameter update is biased towards some dominant classes.
arXiv Detail & Related papers (2023-01-30T15:54:00Z) - Robust Continual Test-time Adaptation: Instance-aware BN and
Prediction-balanced Memory [58.72445309519892]
We present a new test-time adaptation scheme that is robust against non-i.i.d. test data streams.
Our novelty is mainly two-fold: (a) Instance-Aware Batch Normalization (IABN) that corrects normalization for out-of-distribution samples, and (b) Prediction-balanced Reservoir Sampling (PBRS) that simulates i.i.d. data stream from non-i.i.d. stream in a class-balanced manner.
arXiv Detail & Related papers (2022-08-10T03:05:46Z) - CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time.
We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
arXiv Detail & Related papers (2022-06-01T03:02:07Z) - Efficient Test-Time Model Adaptation without Forgetting [60.36499845014649]
Test-time adaptation seeks to tackle potential distribution shifts between training and testing data.
We propose an active sample selection criterion to identify reliable and non-redundant samples.
We also introduce a Fisher regularizer to constrain important model parameters from drastic changes.
arXiv Detail & Related papers (2022-04-06T06:39:40Z) - Listen, Adapt, Better WER: Source-free Single-utterance Test-time
Adaptation for Automatic Speech Recognition [65.84978547406753]
Test-time Adaptation aims to adapt the model trained on source domains to yield better predictions for test samples.
Single-Utterance Test-time Adaptation (SUTA) is the first TTA study in speech area to our best knowledge.
arXiv Detail & Related papers (2022-03-27T06:38:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.