Detecting OOD Samples via Optimal Transport Scoring Function

• URL: http://arxiv.org/abs/2502.16115v1
• Date: Sat, 22 Feb 2025 06:37:18 GMT
• Title: Detecting OOD Samples via Optimal Transport Scoring Function
• Authors: Heng Gao, Zhuolin He, Jian Pu,
• Abstract summary: We propose a novel score function based on the optimal transport theory, named OTOD, for OOD detection.<n>We utilize information from features, logits, and the softmax probability space to calculate the OOD score for each test sample.<n>Our experiments show that combining this information can boost the performance of OTOD with a certain margin.
• Score: 5.093257685701887
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To deploy machine learning models in the real world, researchers have proposed many OOD detection algorithms to help models identify unknown samples during the inference phase and prevent them from making untrustworthy predictions. Unlike methods that rely on extra data for outlier exposure training, post hoc methods detect Out-of-Distribution (OOD) samples by developing scoring functions, which are model agnostic and do not require additional training. However, previous post hoc methods may fail to capture the geometric cues embedded in network representations. Thus, in this study, we propose a novel score function based on the optimal transport theory, named OTOD, for OOD detection. We utilize information from features, logits, and the softmax probability space to calculate the OOD score for each test sample. Our experiments show that combining this information can boost the performance of OTOD with a certain margin. Experiments on the CIFAR-10 and CIFAR-100 benchmarks demonstrate the superior performance of our method. Notably, OTOD outperforms the state-of-the-art method GEN by 7.19% in the mean FPR@95 on the CIFAR-10 benchmark using ResNet-18 as the backbone, and by 12.51% in the mean FPR@95 using WideResNet-28 as the backbone. In addition, we provide theoretical guarantees for OTOD. The code is available in https://github.com/HengGao12/OTOD.

Related papers

• SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation [5.590633742488972]
  Out-of-distribution (OOD) detection is crucial for the safe deployment of neural networks. We propose SeTAR, a training-free OOD detection method. SeTAR enhances OOD detection via post-hoc modification of the model's weight matrices using a simple greedy search algorithm. Our work offers a scalable, efficient solution for OOD detection, setting a new state-of-the-art in this area.
  arXiv  Detail & Related papers  (2024-06-18T13:55:13Z)
• GOODAT: Towards Test-time Graph Out-of-Distribution Detection [103.40396427724667]
  Graph neural networks (GNNs) have found widespread application in modeling graph data across diverse domains. Recent studies have explored graph OOD detection, often focusing on training a specific model or modifying the data on top of a well-trained GNN. This paper introduces a data-centric, unsupervised, and plug-and-play solution that operates independently of training data and modifications of GNN architecture.
  arXiv  Detail & Related papers  (2024-01-10T08:37:39Z)
• MOODv2: Masked Image Modeling for Out-of-Distribution Detection [57.17163962383442]
  This study explores distinct pretraining tasks and employing various OOD score functions. Our framework, MOODv2, impressively enhances 14.30% AUROC to 95.68% on ImageNet and achieves 99.98% on CIFAR-10.
  arXiv  Detail & Related papers  (2024-01-05T02:57:58Z)
• Out-of-distribution Object Detection through Bayesian Uncertainty Estimation [10.985423935142832]
  We propose a novel, intuitive, and scalable probabilistic object detection method for OOD detection. Our method is able to distinguish between in-distribution (ID) data and OOD data via weight parameter sampling from proposed Gaussian distributions. We demonstrate that our Bayesian object detector can achieve satisfactory OOD identification performance by reducing the FPR95 score by up to 8.19% and increasing the AUROC score by up to 13.94% when trained on BDD100k and VOC datasets.
  arXiv  Detail & Related papers  (2023-10-29T19:10:52Z)
• Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability [70.72426887518517]
  Out-of-distribution (OOD) detection is an indispensable aspect of secure AI when deploying machine learning models in real-world applications. We propose a novel method, Unleashing Mask, which aims to restore the OOD discriminative capabilities of the well-trained model with ID data. Our method utilizes a mask to figure out the memorized atypical samples, and then finetune the model or prune it with the introduced mask to forget them.
  arXiv  Detail & Related papers  (2023-06-06T14:23:34Z)
• SIO: Synthetic In-Distribution Data Benefits Out-of-Distribution Detection [34.97444309333315]
  We develop a data-driven approach to building reliable Out-of-Distribution (OOD) detectors. We exploit the internal in-distribution (ID) training set by utilizing generative models to produce additional synthetic ID images. Our training framework, which is termed SIO, serves as a "plug-and-play" technique that is designed to be compatible with existing and future OOD detection algorithms.
  arXiv  Detail & Related papers  (2023-03-25T18:34:34Z)
• AUTO: Adaptive Outlier Optimization for Online Test-Time OOD Detection [81.49353397201887]
  Out-of-distribution (OOD) detection is crucial to deploying machine learning models in open-world applications. We introduce a novel paradigm called test-time OOD detection, which utilizes unlabeled online data directly at test time to improve OOD detection performance. We propose adaptive outlier optimization (AUTO), which consists of an in-out-aware filter, an ID memory bank, and a semantically-consistent objective.
  arXiv  Detail & Related papers  (2023-03-22T02:28:54Z)
• Effective Robustness against Natural Distribution Shifts for Models with Different Training Data [113.21868839569]
  "Effective robustness" measures the extra out-of-distribution robustness beyond what can be predicted from the in-distribution (ID) performance. We propose a new evaluation metric to evaluate and compare the effective robustness of models trained on different data.
  arXiv  Detail & Related papers  (2023-02-02T19:28:41Z)
• A Simple Test-Time Method for Out-of-Distribution Detection [45.11199798139358]
  This paper proposes a simple Test-time Linear Training (ETLT) method for OOD detection. We find that the probabilities of input images being out-of-distribution are surprisingly linearly correlated to the features extracted by neural networks. We propose an online variant of the proposed method, which achieves promising performance and is more practical in real-world applications.
  arXiv  Detail & Related papers  (2022-07-17T16:02:58Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)
• EARLIN: Early Out-of-Distribution Detection for Resource-efficient Collaborative Inference [4.826988182025783]
  Collaborative inference enables resource-constrained edge devices to make inferences by uploading inputs to a server. While this setup works cost-effectively for successful inferences, it severely underperforms when the model faces input samples on which the model was not trained. We propose a novel lightweight OOD detection approach that mines important features from the shallow layers of a pretrained CNN model.
  arXiv  Detail & Related papers  (2021-06-25T18:43:23Z)
• Probabilistic Trust Intervals for Out of Distribution Detection [8.35564578781252]
  We propose a straightforward yet novel technique to enhance OOD detection in pre-trained networks without altering its original parameters.<n>Our approach defines probabilistic trust intervals for each network weight, determined using in-distribution data.<n>We evaluate our approach on MNIST, Fashion-MNIST, CIFAR-10, CIFAR-100 and CIFAR-10-C.
  arXiv  Detail & Related papers  (2021-02-02T06:23:04Z)

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.