Feature-Based Instance Neighbor Discovery: Advanced Stable Test-Time Adaptation in Dynamic World

• URL: http://arxiv.org/abs/2506.06782v1
• Date: Sat, 07 Jun 2025 12:45:49 GMT
• Title: Feature-Based Instance Neighbor Discovery: Advanced Stable Test-Time Adaptation in Dynamic World
• Authors: Qinting Jiang, Chuyang Ye, Dongyan Wei, Bingli Wang, Yuan Xue, Jingyan Jiang, Zhi Wang,
• Abstract summary: Deep neural networks still suffer performance declines under distribution shifts between training and test domains.<n>We propose Feature-based Instance Neighbor Discovery (FIND), which comprises three key components: Layer-wise Feature Disentanglement (LFD), Feature Aware Batch Normalization (FABN) and Selective FABN (S-FABN)<n>Experiments demonstrate FIND significantly outperforms existing methods, achieving a 30% accuracy improvement in dynamic scenarios.
• Score: 7.9346432903946535
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite progress, deep neural networks still suffer performance declines under distribution shifts between training and test domains, leading to a substantial decrease in Quality of Experience (QoE) for applications. Existing test-time adaptation (TTA) methods are challenged by dynamic, multiple test distributions within batches. We observe that feature distributions across different domains inherently cluster into distinct groups with varying means and variances. This divergence reveals a critical limitation of previous global normalization strategies in TTA, which inevitably distort the original data characteristics. Based on this insight, we propose Feature-based Instance Neighbor Discovery (FIND), which comprises three key components: Layer-wise Feature Disentanglement (LFD), Feature Aware Batch Normalization (FABN) and Selective FABN (S-FABN). LFD stably captures features with similar distributions at each layer by constructing graph structures. While FABN optimally combines source statistics with test-time distribution specific statistics for robust feature representation. Finally, S-FABN determines which layers require feature partitioning and which can remain unified, thereby enhancing inference efficiency. Extensive experiments demonstrate that FIND significantly outperforms existing methods, achieving a 30\% accuracy improvement in dynamic scenarios while maintaining computational efficiency.

Related papers

• Unified modality separation: A vision-language framework for unsupervised domain adaptation [60.8391821117794]
  Unsupervised domain adaptation (UDA) enables models trained on a labeled source domain to handle new unlabeled domains.<n>We propose a unified modality separation framework that accommodates both modality-specific and modality-invariant components.<n>Our methods achieve up to 9% performance gain with 9 times of computational efficiencies.
  arXiv  Detail & Related papers  (2025-08-07T02:51:10Z)
• Matcha: Mitigating Graph Structure Shifts with Test-Time Adaptation [66.40525136929398]
  Test-time adaptation (TTA) has attracted attention due to its ability to adapt a pre-trained model to a target domain, without re-accessing the source domain.<n>We propose Matcha, an innovative framework designed for effective and efficient adaptation to structure shifts in graphs.<n>We validate the effectiveness of Matcha on both synthetic and real-world datasets, demonstrating its robustness across various combinations of structure and attribute shifts.
  arXiv  Detail & Related papers  (2024-10-09T15:15:40Z)
• IT$^3$: Idempotent Test-Time Training [95.78053599609044]
  Deep learning models often struggle when deployed in real-world settings due to distribution shifts between training and test data.<n>We present Idempotent Test-Time Training (IT$3$), a novel approach that enables on-the-fly adaptation to distribution shifts using only the current test instance.<n>Our results suggest that idempotence provides a universal principle for test-time adaptation that generalizes across domains and architectures.
  arXiv  Detail & Related papers  (2024-10-05T15:39:51Z)
• DATTA: Towards Diversity Adaptive Test-Time Adaptation in Dynamic Wild World [6.816521410643928]
  This paper proposes a new general method, named Diversity Adaptive Test-Time Adaptation (DATTA), aimed at improving Quality of Experience (QoE) It features three key components: Diversity Discrimination (DD) to assess batch diversity, Diversity Adaptive Batch Normalization (DABN) to tailor normalization methods based on DD insights, and Diversity Adaptive Fine-Tuning (DAFT) to selectively fine-tune the model. Experimental results show that our method achieves up to a 21% increase in accuracy compared to state-of-the-art methodologies.
  arXiv  Detail & Related papers  (2024-08-15T09:50:11Z)
• Discover Your Neighbors: Advanced Stable Test-Time Adaptation in Dynamic World [8.332531696256666]
  Discover Your Neighbours (DYN) is the first backward-free approach specialized for dynamic test-time adaptation (TTA) Our DYN consists of layer-wise instance statistics clustering (LISC) and cluster-aware batch normalization (CABN) Experimental results validate DYN's robustness and effectiveness, demonstrating maintained performance under dynamic data stream patterns.
  arXiv  Detail & Related papers  (2024-06-08T09:22:32Z)
• Test-Time Domain Generalization for Face Anti-Spoofing [60.94384914275116]
  Face Anti-Spoofing (FAS) is pivotal in safeguarding facial recognition systems against presentation attacks. We introduce a novel Test-Time Domain Generalization framework for FAS, which leverages the testing data to boost the model's generalizability. Our method, consisting of Test-Time Style Projection (TTSP) and Diverse Style Shifts Simulation (DSSS), effectively projects the unseen data to the seen domain space.
  arXiv  Detail & Related papers  (2024-03-28T11:50:23Z)
• Enhancing Out-of-Distribution Detection with Multitesting-based Layer-wise Feature Fusion [11.689517005768046]
  Out-of-distribution samples may exhibit shifts in local or global features compared to the training distribution. We propose a novel framework, Multitesting-based Layer-wise Out-of-Distribution (OOD) Detection. Our scheme effectively enhances the performance of out-of-distribution detection when compared to baseline methods.
  arXiv  Detail & Related papers  (2024-03-16T04:35:04Z)
• Distributional Shift Adaptation using Domain-Specific Features [41.91388601229745]
  In open-world scenarios, streaming big data can be Out-Of-Distribution (OOD) We propose a simple yet effective approach that relies on correlations in general regardless of whether the features are invariant or not. Our approach uses the most confidently predicted samples identified by an OOD base model to train a new model that effectively adapts to the target domain.
  arXiv  Detail & Related papers  (2022-11-09T04:16:21Z)
• Covariance-aware Feature Alignment with Pre-computed Source Statistics for Test-time Adaptation to Multiple Image Corruptions [11.859913430860335]
  Real-world image recognition systems often face corrupted input images, which cause distribution shifts and degrade the performance of models. Test-time adaptation (TTA) is one of the settings that can address this problem. We propose a novel TTA method named Covariance-Aware Feature alignment (CAFe) to address the distribution gap during testing.
  arXiv  Detail & Related papers  (2022-04-28T02:50:43Z)
• Self-Challenging Improves Cross-Domain Generalization [81.99554996975372]
  Convolutional Neural Networks (CNN) conduct image classification by activating dominant features that correlated with labels. We introduce a simple training, Self-Challenging Representation (RSC), that significantly improves the generalization of CNN to the out-of-domain data. RSC iteratively challenges the dominant features activated on the training data, and forces the network to activate remaining features that correlates with labels.
  arXiv  Detail & Related papers  (2020-07-05T21:42:26Z)
• Feature Quantization Improves GAN Training [126.02828112121874]
  Feature Quantization (FQ) for the discriminator embeds both true and fake data samples into a shared discrete space. Our method can be easily plugged into existing GAN models, with little computational overhead in training.
  arXiv  Detail & Related papers  (2020-04-05T04:06:50Z)
• Dynamic Federated Learning [57.14673504239551]
  Federated learning has emerged as an umbrella term for centralized coordination strategies in multi-agent environments. We consider a federated learning model where at every iteration, a random subset of available agents perform local updates based on their data. Under a non-stationary random walk model on the true minimizer for the aggregate optimization problem, we establish that the performance of the architecture is determined by three factors, namely, the data variability at each agent, the model variability across all agents, and a tracking term that is inversely proportional to the learning rate of the algorithm.
  arXiv  Detail & Related papers  (2020-02-20T15:00:54Z)

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.