Shaping Parameter Contribution Patterns for Out-of-Distribution Detection

• URL: http://arxiv.org/abs/2603.07195v1
• Date: Sat, 07 Mar 2026 13:13:42 GMT
• Title: Shaping Parameter Contribution Patterns for Out-of-Distribution Detection
• Abstract summary: We show that trained classifiers tend to rely on sparse parameter contribution patterns.<n>This brittleness can be exploited by OOD inputs that anomalously trigger these parameters, resulting in overconfident predictions.<n>To address this issue, we propose a simple yet effective method called Shaping Contribution Patterns (SPCP)
• Score: 6.294911773583837
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Out-of-distribution (OOD) detection is a well-known challenge due to deep models often producing overconfident. In this paper, we reveal a key insight that trained classifiers tend to rely on sparse parameter contribution patterns, meaning that only a few dominant parameters drive predictions. This brittleness can be exploited by OOD inputs that anomalously trigger these parameters, resulting in overconfident predictions. To address this issue, we propose a simple yet effective method called Shaping Parameter Contribution Patterns (SPCP), which enhances OOD detection robustness by encouraging the classifier to learn boundary-oriented dense contribution patterns. Specifically, SPCP operates during training by rectifying excessively high parameter contributions based on a dynamically estimated threshold. This mechanism promotes the classifier to rely on a broader set of parameters for decision-making, thereby reducing the risk of overconfident predictions caused by anomalously triggered parameters, while preserving in-distribution (ID) performance. Extensive experiments under various OOD detection setups verify the effectiveness of SPCP.

Related papers

• FACTOR: Counterfactual Training-Free Test-Time Adaptation for Open-Vocabulary Object Detection [63.91351553178842]
  FACTOR is a training-free Test-time adaptation for Open-vocabulary object detection.<n>It quantifies attribute sensitivity, semantic relevance, and prediction variation to selectively suppress attribute-dependent predictions.<n>Experiments on PASCAL-C, COCO-C, and FoggyCityscapes show that FACTOR consistently outperforms prior TTA methods.
  arXiv  Detail & Related papers  (2026-05-05T02:31:18Z)
• PROMISE: Process Reward Models Unlock Test-Time Scaling Laws in Generative Recommendations [52.67948063133533]
  Generative Recommendation has emerged as a promising paradigm, reformulating recommendation as a sequence-to-sequence generation task over hierarchical Semantic IDs.<n>Existing methods suffer from a critical issue we term Semantic Drift, where errors in early, high-level tokens irreversibly divert the generation trajectory into irrelevant semantic subspaces.<n>We propose Promise, a novel framework that integrates dense, step-by-step verification into generative models.
  arXiv  Detail & Related papers  (2026-01-08T07:38:46Z)
• Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios [54.58186816693791]
  environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption.<n>We propose a new mechanism, converting the fine-tuning process to a specific- parameter generation.<n>In particular, we first design a dual-path LoRA-based domain-aware adapter that disentangles features into domain-invariant and domain-specific components.
  arXiv  Detail & Related papers  (2025-06-30T17:14:12Z)
• EKPC: Elastic Knowledge Preservation and Compensation for Class-Incremental Learning [53.88000987041739]
  Class-Incremental Learning (CIL) aims to enable AI models to continuously learn from sequentially arriving data of different classes over time.<n>We propose the Elastic Knowledge Preservation and Compensation (EKPC) method, integrating Importance-aware importance Regularization (IPR) and Trainable Semantic Drift Compensation (TSDC) for CIL.
  arXiv  Detail & Related papers  (2025-06-14T05:19:58Z)
• TULiP: Test-time Uncertainty Estimation via Linearization and Weight Perturbation [11.334867025651233]
  We propose TULiP, a theoretically-driven uncertainty estimator for OOD detection.<n>Our approach considers a hypothetical perturbation applied to the network before convergence.<n>Our method exhibits state-of-the-art performance, particularly for near-distribution samples.
  arXiv  Detail & Related papers  (2025-05-22T17:16:41Z)
• The Role of Hyperparameters in Predictive Multiplicity [0.0]
  Different machine learning models trained on the same dataset yield divergent predictions for identical inputs.<n>These inconsistencies can seriously impact high-stakes decisions such as credit assessments, hiring, and medical diagnoses.
  arXiv  Detail & Related papers  (2025-03-13T19:22:44Z)
• ITP: Instance-Aware Test Pruning for Out-of-Distribution Detection [4.035215689271819]
  Out-of-distribution (OOD) detection is crucial for ensuring the reliable deployment of deep models in real-world scenarios.<n>We propose a simple yet effective post-hoc method called Instance-aware Test Pruning (ITP)<n>ITP performs OOD detection by considering both coarse-grained and fine-grained levels of parameter pruning.
  arXiv  Detail & Related papers  (2024-12-17T05:49:26Z)
• Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack [12.647669152300871]
  We study the complexities of adversarial attack algorithms, dissecting the adversarial process into two critical phases: the Directional Supervision Process (DSP) and the Directional Optimization Process (DOP) The impact of models on adversarial efficacy is often overlooked in current research, leading to neglect of DSP. We propose that under certain conditions, fine-tuning model parameters can significantly enhance the quality of DSP.
  arXiv  Detail & Related papers  (2024-08-14T17:51:15Z)
• IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency [20.61046457594186]
  Deep neural networks (DNNs) are vulnerable to backdoor attacks. This paper proposes a simple yet effective input-level backdoor detection (dubbed IBD-PSC) to filter out malicious testing images.
  arXiv  Detail & Related papers  (2024-05-16T03:19:52Z)
• Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective [65.10019978876863]
  Diffusion-Based Purification (DBP) has emerged as an effective defense mechanism against adversarial attacks.<n>In this paper, we propose that the intrinsicity in the DBP process is the primary factor driving robustness.
  arXiv  Detail & Related papers  (2024-04-22T16:10:38Z)
• Free Lunch for Generating Effective Outlier Supervision [46.37464572099351]
  We propose an ultra-effective method to generate near-realistic outlier supervision. Our proposed textttBayesAug significantly reduces the false positive rate over 12.50% compared with the previous schemes.
  arXiv  Detail & Related papers  (2023-01-17T01:46:45Z)
• Diffusion Denoising Process for Perceptron Bias in Out-of-distribution Detection [67.49587673594276]
  We introduce a new perceptron bias assumption that suggests discriminator models are more sensitive to certain features of the input, leading to the overconfidence problem. We demonstrate that the diffusion denoising process (DDP) of DMs serves as a novel form of asymmetric, which is well-suited to enhance the input and mitigate the overconfidence problem. Our experiments on CIFAR10, CIFAR100, and ImageNet show that our method outperforms SOTA approaches.
  arXiv  Detail & Related papers  (2022-11-21T08:45:08Z)

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.