Noise-Aware Generalization: Robustness to In-Domain Noise and Out-of-Domain Generalization

• URL: http://arxiv.org/abs/2504.02996v1
• Date: Thu, 03 Apr 2025 19:37:57 GMT
• Title: Noise-Aware Generalization: Robustness to In-Domain Noise and Out-of-Domain Generalization
• Authors: Siqi Wang, Aoming Liu, Bryan A. Plummer,
• Abstract summary: Multi-source Domain Generalization (DG) aims to improve model robustness to new distributions.<n>However, DG methods often overlook the effect of label noise, which can confuse a model during training, reducing performance.<n>In this paper, we investigate this underexplored space, where models are evaluated under both distribution shifts and label noise.<n>Our proposed DL4ND approach improves noise detection by taking advantage of the observation that noisy samples that may appear indistinguishable within a single domain often show greater variation when compared across domains.
• Score: 19.405975017917957
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-source Domain Generalization (DG) aims to improve model robustness to new distributions. However, DG methods often overlook the effect of label noise, which can confuse a model during training, reducing performance. Limited prior work has analyzed DG method's noise-robustness, typically focused on an analysis of existing methods rather than new solutions. In this paper, we investigate this underexplored space, where models are evaluated under both distribution shifts and label noise, which we refer to as Noise-Aware Generalization (NAG). A natural solution to address label noise would be to combine a Learning with Noisy Labels (LNL) method with those from DG. Many LNL methods aim to detect distribution shifts in a class's samples, i.e., they assume that distribution shifts often correspond to label noise. However, in NAG distribution shifts can be due to label noise or domain shifts, breaking the assumptions used by LNL methods. A naive solution is to make a similar assumption made by many DG methods, where we presume to have domain labels during training, enabling us to isolate the two types of shifts. However, this ignores valuable cross-domain information. Specifically, our proposed DL4ND approach improves noise detection by taking advantage of the observation that noisy samples that may appear indistinguishable within a single domain often show greater variation when compared across domains. Experiments show that DL4ND significantly improves performance across four diverse datasets, offering a promising direction for tackling NAG.

Related papers

• A Language Anchor-Guided Method for Robust Noisy Domain Generalization [20.83580289888522]
  We introduce Anchor Alignment and Adaptive Weighting (A3W)<n>A3W uses sample reweighting guided by natural language processing (NLP) anchors to extract more representative features.<n>It consistently outperforms state-of-the-art domain generalization methods.
  arXiv  Detail & Related papers  (2025-03-21T15:20:28Z)
• Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization [40.7795100916718]
  Open-Set Domain Generalization is a challenging task requiring models to accurately predict familiar categories. Label noise can mislead model optimization, exacerbating the challenges of open-set recognition in novel domains. We propose HyProMeta, a framework that integrates hyperbolic category prototypes for label noise-aware meta-learning.
  arXiv  Detail & Related papers  (2024-12-24T11:00:23Z)
• Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts [56.57141696245328]
  In open-world scenarios, where both novel classes and domains may exist, an ideal segmentation model should detect anomaly classes for safety. Existing methods often struggle to distinguish between domain-level and semantic-level distribution shifts.
  arXiv  Detail & Related papers  (2024-11-06T11:03:02Z)
• Robustness to Subpopulation Shift with Domain Label Noise via Regularized Annotation of Domains [27.524318404316013]
  We introduce Regularized reliant of Domains (RAD) in order to train robust last layer classifiers without the need for explicit domain annotations. RAD outperforms state-of-the-art annotation-reliant methods even with only 5% noise in the training data for several publicly available datasets.
  arXiv  Detail & Related papers  (2024-02-16T19:35:42Z)
• Feature Noise Boosts DNN Generalization under Label Noise [65.36889005555669]
  The presence of label noise in the training data has a profound impact on the generalization of deep neural networks (DNNs) In this study, we introduce and theoretically demonstrate a simple feature noise method, which directly adds noise to the features of training data.
  arXiv  Detail & Related papers  (2023-08-03T08:31:31Z)
• Generative Model Based Noise Robust Training for Unsupervised Domain Adaptation [108.11783463263328]
  This paper proposes a Generative model-based Noise-Robust Training method (GeNRT) It eliminates domain shift while mitigating label noise. Experiments on Office-Home, PACS, and Digit-Five show that our GeNRT achieves comparable performance to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-03-10T06:43:55Z)
• Latent Class-Conditional Noise Model [54.56899309997246]
  We introduce a Latent Class-Conditional Noise model (LCCN) to parameterize the noise transition under a Bayesian framework. We then deduce a dynamic label regression method for LCCN, whose Gibbs sampler allows us efficiently infer the latent true labels. Our approach safeguards the stable update of the noise transition, which avoids previous arbitrarily tuning from a mini-batch of samples.
  arXiv  Detail & Related papers  (2023-02-19T15:24:37Z)
• Neighborhood Collective Estimation for Noisy Label Identification and Correction [92.20697827784426]
  Learning with noisy labels (LNL) aims at designing strategies to improve model performance and generalization by mitigating the effects of model overfitting to noisy labels. Recent advances employ the predicted label distributions of individual samples to perform noise verification and noisy label correction, easily giving rise to confirmation bias. We propose Neighborhood Collective Estimation, in which the predictive reliability of a candidate sample is re-estimated by contrasting it against its feature-space nearest neighbors.
  arXiv  Detail & Related papers  (2022-08-05T14:47:22Z)
• Adaptive Pseudo-Label Refinement by Negative Ensemble Learning for Source-Free Unsupervised Domain Adaptation [35.728603077621564]
  Existing Unsupervised Domain Adaptation (UDA) methods presumes source and target domain data to be simultaneously available during training. A pre-trained source model is always considered to be available, even though performing poorly on target due to the well-known domain shift problem. We propose a unified method to tackle adaptive noise filtering and pseudo-label refinement.
  arXiv  Detail & Related papers  (2021-03-29T22:18:34Z)
• Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model [80.91927573604438]
  This paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances. Experiments on datasets with both synthetic and real-world label noise verify that the proposed method yields significant improvements on robustness.
  arXiv  Detail & Related papers  (2021-01-14T05:43:51Z)

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.