IMSE: Intrinsic Mixture of Spectral Experts Fine-tuning for Test-Time Adaptation

• URL: http://arxiv.org/abs/2603.07926v2
• Date: Tue, 10 Mar 2026 03:16:45 GMT
• Title: IMSE: Intrinsic Mixture of Spectral Experts Fine-tuning for Test-Time Adaptation
• Abstract summary: Test-time adaptation has been widely explored to prevent performance degradation when test data differ from the distribution.<n>We propose Intrinsic Mixture of Spectral Experts (IMSE) that leverages the spectral experts embedded in Vision Transformers.<n>Our method achieves state-of-the-art performance on various distribution-shift benchmarks under the TTA setting.
• Score: 16.129735356928958
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Test-time adaptation (TTA) has been widely explored to prevent performance degradation when test data differ from the training distribution. However, fully leveraging the rich representations of large pretrained models with minimal parameter updates remains underexplored. In this paper, we propose Intrinsic Mixture of Spectral Experts (IMSE) that leverages the spectral experts inherently embedded in Vision Transformers. We decompose each linear layer via singular value decomposition (SVD) and adapt only the singular values, while keeping the singular vectors fixed. We further identify a key limitation of entropy minimization in TTA: it often induces feature collapse, causing the model to rely on domain-specific features rather than class-discriminative features. To address this, we propose a diversity maximization loss based on expert-input alignment, which encourages diverse utilization of spectral experts during adaptation. In the continual test-time adaptation (CTTA) scenario, beyond preserving pretrained knowledge, it is crucial to retain and reuse knowledge from previously observed domains. We introduce Domain-Aware Spectral Code Retrieval, which estimates input distributions to detect domain shifts, and retrieves adapted singular values for rapid adaptation. Consequently, our method achieves state-of-the-art performance on various distribution-shift benchmarks under the TTA setting. In CTTA and Gradual CTTA, it further improves accuracy by 3.4 percentage points (pp) and 2.4 pp, respectively, while requiring 385 times fewer trainable parameters. Our code is available at https://github.com/baek85/IMSE.

Related papers

• Multi-Hypothesis Test-Time Adaptation to Mitigate Underspecification [36.471308624288035]
  Test-Time Adaptation (TTA) seeks to improve model robustness under distribution shifts by adapting parameters using unlabeled target data.<n>In the absence of supervision, entropy-based adaptation is fundamentally underconstrained: multiple distinct parameter updates can achieve similarly low entropy while inducing drastically different decision boundaries.<n>We reinterpret TTA through a posterior-inspired lens induced by entropy minimization, where low-entropy solutions define a pseudo-likelihood over parameters.
  arXiv  Detail & Related papers  (2026-06-30T23:12:36Z)
• BayesTTA: Continual-Temporal Test-Time Adaptation for Vision-Language Models via Gaussian Discriminant Analysis [41.09181390655176]
  Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but degrade significantly under textittemporally evolving distribution shifts common in real-world scenarios.<n>We formalize this practical problem as textitContinual-Temporal Test-Time Adaptation (CT-TTA), where test distributions evolve gradually over time.<n>We propose textitBayesTTA, a Bayesian adaptation framework that enforces temporally consistent predictions and dynamically aligns visual representations.
  arXiv  Detail & Related papers  (2025-07-11T14:02:54Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• Evolutionary Retrofitting [42.21143557577615]
  AfterLearnER consists in applying non-differentiable optimization, including evolutionary methods, to fully-trained machine learning models. The efficiency of AfterLearnER is demonstrated by tackling non-differentiable signals such as threshold-based criteria in depth sensing, the word error rate in speech re-synthesis, image quality in 3D generative adversarial networks (GANs) The advantages of AfterLearnER are its versatility (no gradient is needed), the possibility to use non-differentiable feedback including human evaluations, the limited overfitting, supported by a theoretical study and its anytime behavior.
  arXiv  Detail & Related papers  (2024-10-15T06:59:32Z)
• Enhancing Test Time Adaptation with Few-shot Guidance [62.49199492255226]
  Deep neural networks often encounter significant performance drops while facing with domain shifts between training (source) and test (target) data.<n>Test Time Adaptation (TTA) methods have been proposed to adapt pre-trained source model to handle out-of-distribution streaming target data.<n>We develop Few-Shot Test Time Adaptation (FS-TTA), a novel and practical setting that utilizes a few-shot support set on top of TTA.
  arXiv  Detail & Related papers  (2024-09-02T15:50:48Z)
• Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation [37.79819260918366]
  Continual Test-Time Adaptation (CTTA) aims to adapt the pre-trained model to ever-evolving target domains. We explore the integration of a Mixture-of-Activation-Sparsity-Experts (MoASE) as an adapter for the CTTA task.
  arXiv  Detail & Related papers  (2024-05-26T08:51:39Z)
• Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition [30.350005654271868]
  Test-Time Adaptation aims to utilize the test stream to adjust predictions in real-time inference. High computational cost makes it intractable to run on resource-constrained edge devices. We propose an Optimization-Free Test-Time Adaptation framework for sensor-based HAR.
  arXiv  Detail & Related papers  (2023-10-28T02:20:33Z)
• AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation [64.9230895853942]
  Domain generalization can be arbitrarily hard without exploiting target domain information. Test-time adaptive (TTA) methods are proposed to address this issue. In this work, we adopt Non-Parametric to perform the test-time Adaptation (AdaNPC)
  arXiv  Detail & Related papers  (2023-04-25T04:23:13Z)
• Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection [58.789823426981044]
  We propose a novel auxiliary loss formulation that aims to align the class confidence of bounding boxes with the accurateness of predictions. Our results reveal that our train-time loss surpasses strong calibration baselines in reducing calibration error for both in and out-domain scenarios.
  arXiv  Detail & Related papers  (2023-03-25T08:56:21Z)
• Sample-Efficient Optimisation with Probabilistic Transformer Surrogates [66.98962321504085]
  This paper investigates the feasibility of employing state-of-the-art probabilistic transformers in Bayesian optimisation. We observe two drawbacks stemming from their training procedure and loss definition, hindering their direct deployment as proxies in black-box optimisation. We introduce two components: 1) a BO-tailored training prior supporting non-uniformly distributed points, and 2) a novel approximate posterior regulariser trading-off accuracy and input sensitivity to filter favourable stationary points for improved predictive performance.
  arXiv  Detail & Related papers  (2022-05-27T11:13:17Z)
• Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift [81.74795324629712]
  We call prediction-time batch normalization, which significantly improves model accuracy and calibration under covariate shift. We show that prediction-time batch normalization provides complementary benefits to existing state-of-the-art approaches for improving robustness. The method has mixed results when used alongside pre-training, and does not seem to perform as well under more natural types of dataset shift.
  arXiv  Detail & Related papers  (2020-06-19T05:08:43Z)

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.