Decoupled Prototype Learning for Reliable Test-Time Adaptation
- URL: http://arxiv.org/abs/2401.08703v2
- Date: Thu, 25 Jan 2024 11:09:38 GMT
- Title: Decoupled Prototype Learning for Reliable Test-Time Adaptation
- Authors: Guowei Wang, Changxing Ding, Wentao Tan, Mingkui Tan
- Abstract summary: Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the target domain during inference.
One popular approach involves fine-tuning model with cross-entropy loss according to estimated pseudo-labels.
This study reveals that minimizing the classification error of each sample causes the cross-entropy loss's vulnerability to label noise.
We propose a novel Decoupled Prototype Learning (DPL) method that features prototype-centric loss computation.
- Score: 50.779896759106784
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Test-time adaptation (TTA) is a task that continually adapts a pre-trained
source model to the target domain during inference. One popular approach
involves fine-tuning model with cross-entropy loss according to estimated
pseudo-labels. However, its performance is significantly affected by noisy
pseudo-labels. This study reveals that minimizing the classification error of
each sample causes the cross-entropy loss's vulnerability to label noise. To
address this issue, we propose a novel Decoupled Prototype Learning (DPL)
method that features prototype-centric loss computation. First, we decouple the
optimization of class prototypes. For each class prototype, we reduce its
distance with positive samples and enlarge its distance with negative samples
in a contrastive manner. This strategy prevents the model from overfitting to
noisy pseudo-labels. Second, we propose a memory-based strategy to enhance
DPL's robustness for the small batch sizes often encountered in TTA. We update
each class's pseudo-feature from a memory in a momentum manner and insert an
additional DPL loss. Finally, we introduce a consistency regularization-based
approach to leverage samples with unconfident pseudo-labels. This approach
transfers feature styles of samples with unconfident pseudo-labels to those
with confident pseudo-labels. Thus, more reliable samples for TTA are created.
The experimental results demonstrate that our methods achieve state-of-the-art
performance on domain generalization benchmarks, and reliably improve the
performance of self-training-based methods on image corruption benchmarks. The
code will be released.
Related papers
- PS-TTL: Prototype-based Soft-labels and Test-Time Learning for Few-shot Object Detection [21.443060372419286]
Few-Shot Object Detection (FSOD) has gained widespread attention and made significant progress.
We propose a new framework for FSOD, namely Prototype-based Soft-labels and Test-Time Learning (PS-TTL)
arXiv Detail & Related papers (2024-08-11T02:21:43Z) - STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay [76.06127233986663]
Test-time adaptation (TTA) aims to address the distribution shift between the training and test data with only unlabeled data at test time.
This paper pays attention to the problem that conducts both sample recognition and outlier rejection during inference while outliers exist.
We propose a new approach called STAble Memory rePlay (STAMP), which performs optimization over a stable memory bank instead of the risky mini-batch.
arXiv Detail & Related papers (2024-07-22T16:25:41Z) - Uncertainty-Aware Pseudo-Label Filtering for Source-Free Unsupervised Domain Adaptation [45.53185386883692]
Source-free unsupervised domain adaptation (SFUDA) aims to enable the utilization of a pre-trained source model in an unlabeled target domain without access to source data.
We propose a method called Uncertainty-aware Pseudo-label-filtering Adaptation (UPA) to efficiently address this issue in a coarse-to-fine manner.
arXiv Detail & Related papers (2024-03-17T16:19:40Z) - All Points Matter: Entropy-Regularized Distribution Alignment for
Weakly-supervised 3D Segmentation [67.30502812804271]
Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where only sparse ground-truth labels are available for learning.
We propose a novel learning strategy to regularize the generated pseudo-labels and effectively narrow the gaps between pseudo-labels and model predictions.
arXiv Detail & Related papers (2023-05-25T08:19:31Z) - Guiding Pseudo-labels with Uncertainty Estimation for Test-Time
Adaptation [27.233704767025174]
Test-Time Adaptation (TTA) is a specific case of Unsupervised Domain Adaptation (UDA) where a model is adapted to a target domain without access to source data.
We propose a novel approach for the TTA setting based on a loss reweighting strategy that brings robustness against the noise that inevitably affects the pseudo-labels.
arXiv Detail & Related papers (2023-03-07T10:04:55Z) - MAPS: A Noise-Robust Progressive Learning Approach for Source-Free
Domain Adaptive Keypoint Detection [76.97324120775475]
Cross-domain keypoint detection methods always require accessing the source data during adaptation.
This paper considers source-free domain adaptive keypoint detection, where only the well-trained source model is provided to the target domain.
arXiv Detail & Related papers (2023-02-09T12:06:08Z) - Rethinking Precision of Pseudo Label: Test-Time Adaptation via
Complementary Learning [10.396596055773012]
We propose a novel complementary learning approach to enhance test-time adaptation.
In test-time adaptation tasks, information from the source domain is typically unavailable.
We highlight that the risk function of complementary labels agrees with their Vanilla loss formula.
arXiv Detail & Related papers (2023-01-15T03:36:33Z) - TTAPS: Test-Time Adaption by Aligning Prototypes using Self-Supervision [70.05605071885914]
We propose a novel modification of the self-supervised training algorithm SwAV that adds the ability to adapt to single test samples.
We show the success of our method on the common benchmark dataset CIFAR10-C.
arXiv Detail & Related papers (2022-05-18T05:43:06Z) - Semi-Supervised Domain Adaptation with Prototypical Alignment and
Consistency Learning [86.6929930921905]
This paper studies how much it can help address domain shifts if we further have a few target samples labeled.
To explore the full potential of landmarks, we incorporate a prototypical alignment (PA) module which calculates a target prototype for each class from the landmarks.
Specifically, we severely perturb the labeled images, making PA non-trivial to achieve and thus promoting model generalizability.
arXiv Detail & Related papers (2021-04-19T08:46:08Z)
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.