Gradient Short-Circuit: Efficient Out-of-Distribution Detection via Feature Intervention

• URL: http://arxiv.org/abs/2507.01417v2
• Date: Fri, 04 Jul 2025 13:12:24 GMT
• Title: Gradient Short-Circuit: Efficient Out-of-Distribution Detection via Feature Intervention
• Authors: Jiawei Gu, Ziyue Qiao, Zechao Li,
• Abstract summary: Out-of-Distribution (OOD) detection is critical for safely deploying deep models in open-world environments.<n>We propose an inference-stage technique to short-circuit those feature coordinates that spurious gradients exploit.<n> Experiments on standard OOD benchmarks show our approach yields substantial improvements.
• Score: 19.580332929984028
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Out-of-Distribution (OOD) detection is critical for safely deploying deep models in open-world environments, where inputs may lie outside the training distribution. During inference on a model trained exclusively with In-Distribution (ID) data, we observe a salient gradient phenomenon: around an ID sample, the local gradient directions for "enhancing" that sample's predicted class remain relatively consistent, whereas OOD samples--unseen in training--exhibit disorganized or conflicting gradient directions in the same neighborhood. Motivated by this observation, we propose an inference-stage technique to short-circuit those feature coordinates that spurious gradients exploit to inflate OOD confidence, while leaving ID classification largely intact. To circumvent the expense of recomputing the logits after this gradient short-circuit, we further introduce a local first-order approximation that accurately captures the post-modification outputs without a second forward pass. Experiments on standard OOD benchmarks show our approach yields substantial improvements. Moreover, the method is lightweight and requires minimal changes to the standard inference pipeline, offering a practical path toward robust OOD detection in real-world applications.

Related papers

• Enhancing Out-of-Distribution Detection with Extended Logit Normalization [8.243349010573242]
  Out-of-distribution (OOD) detection is essential for the safe deployment of machine learning models.<n>Recent advances have explored improved classification losses and representation learning strategies to enhance OOD detection.<n>These methods are often tailored to specific post-hoc detection techniques, limiting their generalizability.
  arXiv  Detail & Related papers  (2025-04-15T17:51:35Z)
• Leveraging Perturbation Robustness to Enhance Out-of-Distribution Detection [15.184096796229115]
  We propose a post-hoc method, Perturbation-Rectified OOD detection (PRO), based on the insight that prediction confidence for OOD inputs is more susceptible to reduction under perturbation than in-distribution (IND) inputs.<n>On a CIFAR-10 model with adversarial training, PRO effectively detects near-OOD inputs, achieving a reduction of more than 10% on FPR@95 compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-24T15:32:33Z)
• Model Reprogramming Outperforms Fine-tuning on Out-of-distribution Data in Text-Image Encoders [56.47577824219207]
  In this paper, we unveil the hidden costs associated with intrusive fine-tuning techniques. We introduce a new model reprogramming approach for fine-tuning, which we name Reprogrammer. Our empirical evidence reveals that Reprogrammer is less intrusive and yields superior downstream models.
  arXiv  Detail & Related papers  (2024-03-16T04:19:48Z)
• GROOD: Gradient-Aware Out-of-Distribution Detection [11.862922321532817]
  Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models in real-world applications.<n>We propose GRadient-aware Out-Of-Distribution detection (GROOD), a method that derives an OOD prototype from synthetic samples and computes class prototypes directly from In-distribution (ID) training data.<n>By analyzing the gradients of a nearest-class-prototype loss function concerning an artificial OOD prototype, our approach achieves a clear separation between in-distribution and OOD samples.
  arXiv  Detail & Related papers  (2023-12-22T04:28:43Z)
• EAT: Towards Long-Tailed Out-of-Distribution Detection [55.380390767978554]
  This paper addresses the challenging task of long-tailed OOD detection. The main difficulty lies in distinguishing OOD data from samples belonging to the tail classes. We propose two simple ideas: (1) Expanding the in-distribution class space by introducing multiple abstention classes, and (2) Augmenting the context-limited tail classes by overlaying images onto the context-rich OOD data.
  arXiv  Detail & Related papers  (2023-12-14T13:47:13Z)
• Detecting Out-of-distribution Examples via Class-conditional Impressions Reappearing [30.938412222724608]
  Out-of-distribution (OOD) detection aims at enhancing standard deep neural networks to distinguish anomalous inputs from original training data. Due to privacy and security, auxiliary data tends to be impractical in a real-world scenario. We propose a data-free method without training on natural data, called Class-Conditional Impressions Reappearing (C2IR)
  arXiv  Detail & Related papers  (2023-03-17T02:55:08Z)
• Energy-based Out-of-Distribution Detection for Graph Neural Networks [76.0242218180483]
  We propose a simple, powerful and efficient OOD detection model for GNN-based learning on graphs, which we call GNNSafe. GNNSafe achieves up to $17.0%$ AUROC improvement over state-of-the-arts and it could serve as simple yet strong baselines in such an under-developed area.
  arXiv  Detail & Related papers  (2023-02-06T16:38:43Z)
• 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)
• On the Importance of Gradients for Detecting Distributional Shifts in the Wild [15.548068221414384]
  We present GradNorm, a simple and effective approach for detecting OOD inputs by utilizing information extracted from the gradient space. GradNorm demonstrates superior performance, reducing the average FPR95 by up to 10.89% compared to the previous best method.
  arXiv  Detail & Related papers  (2021-10-01T05:19:32Z)
• On the Practicality of Deterministic Epistemic Uncertainty [106.06571981780591]
  deterministic uncertainty methods (DUMs) achieve strong performance on detecting out-of-distribution data. It remains unclear whether DUMs are well calibrated and can seamlessly scale to real-world applications.
  arXiv  Detail & Related papers  (2021-07-01T17:59:07Z)
• Learn what you can't learn: Regularized Ensembles for Transductive Out-of-distribution Detection [76.39067237772286]
  We show that current out-of-distribution (OOD) detection algorithms for neural networks produce unsatisfactory results in a variety of OOD detection scenarios. This paper studies how such "hard" OOD scenarios can benefit from adjusting the detection method after observing a batch of the test data. We propose a novel method that uses an artificial labeling scheme for the test data and regularization to obtain ensembles of models that produce contradictory predictions only on the OOD samples in a test batch.
  arXiv  Detail & Related papers  (2020-12-10T16:55:13Z)
• Robust Out-of-distribution Detection for Neural Networks [51.19164318924997]
  We show that existing detection mechanisms can be extremely brittle when evaluating on in-distribution and OOD inputs. We propose an effective algorithm called ALOE, which performs robust training by exposing the model to both adversarially crafted inlier and outlier examples.
  arXiv  Detail & Related papers  (2020-03-21T17:46:28Z)

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.