Mining In-distribution Attributes in Outliers for Out-of-distribution Detection
- URL: http://arxiv.org/abs/2412.11466v1
- Date: Mon, 16 Dec 2024 05:47:35 GMT
- Title: Mining In-distribution Attributes in Outliers for Out-of-distribution Detection
- Authors: Yutian Lei, Luping Ji, Pei Liu,
- Abstract summary: Out-of-distribution (OOD) detection is indispensable for deploying reliable machine learning systems in real-world scenarios.
We propose a structured multi-view-based out-of-distribution detection learning framework, which facilitates rational handling of the intrinsic in-distribution attributes in outliers.
- Score: 5.1314912554605066
- License:
- Abstract: Out-of-distribution (OOD) detection is indispensable for deploying reliable machine learning systems in real-world scenarios. Recent works, using auxiliary outliers in training, have shown good potential. However, they seldom concern the intrinsic correlations between in-distribution (ID) and OOD data. In this work, we discover an obvious correlation that OOD data usually possesses significant ID attributes. These attributes should be factored into the training process, rather than blindly suppressed as in previous approaches. Based on this insight, we propose a structured multi-view-based out-of-distribution detection learning (MVOL) framework, which facilitates rational handling of the intrinsic in-distribution attributes in outliers. We provide theoretical insights on the effectiveness of MVOL for OOD detection. Extensive experiments demonstrate the superiority of our framework to others. MVOL effectively utilizes both auxiliary OOD datasets and even wild datasets with noisy in-distribution data. Code is available at https://github.com/UESTC-nnLab/MVOL.
Related papers
- Out-of-Distribution Detection using Synthetic Data Generation [21.612592503592143]
In- and out-of-distribution (OOD) inputs are crucial for reliable deployment of classification systems.
We present a method that harnesses the generative capabilities of Large Language Models (LLMs) to create high-quality synthetic OOD proxies.
arXiv Detail & Related papers (2025-02-05T16:22:09Z) - 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) - Out-of-distribution Detection Learning with Unreliable
Out-of-distribution Sources [73.28967478098107]
Out-of-distribution (OOD) detection discerns OOD data where the predictor cannot make valid predictions as in-distribution (ID) data.
It is typically hard to collect real out-of-distribution (OOD) data for training a predictor capable of discerning OOD patterns.
We propose a data generation-based learning method named Auxiliary Task-based OOD Learning (ATOL) that can relieve the mistaken OOD generation.
arXiv Detail & Related papers (2023-11-06T16:26:52Z) - Learning to Augment Distributions for Out-of-Distribution Detection [49.12437300327712]
Open-world classification systems should discern out-of-distribution (OOD) data whose labels deviate from those of in-distribution (ID) cases.
We propose Distributional-Augmented OOD Learning (DAL) to alleviating the OOD distribution discrepancy.
arXiv Detail & Related papers (2023-11-03T09:19:33Z) - Diversified Outlier Exposure for Out-of-Distribution Detection via
Informative Extrapolation [110.34982764201689]
Out-of-distribution (OOD) detection is important for deploying reliable machine learning models on real-world applications.
Recent advances in outlier exposure have shown promising results on OOD detection via fine-tuning model with informatively sampled auxiliary outliers.
We propose a novel framework, namely, Diversified Outlier Exposure (DivOE), for effective OOD detection via informative extrapolation based on the given auxiliary outliers.
arXiv Detail & Related papers (2023-10-21T07:16:09Z) - Using Semantic Information for Defining and Detecting OOD Inputs [3.9577682622066264]
Out-of-distribution (OOD) detection has received some attention recently.
We demonstrate that the current detectors inherit the biases in the training dataset.
This can render the current OOD detectors impermeable to inputs lying outside the training distribution but with the same semantic information.
We perform OOD detection on semantic information extracted from the training data of MNIST and COCO datasets.
arXiv Detail & Related papers (2023-02-21T21:31:20Z) - Out-of-Distribution Detection with Hilbert-Schmidt Independence
Optimization [114.43504951058796]
Outlier detection tasks have been playing a critical role in AI safety.
Deep neural network classifiers usually tend to incorrectly classify out-of-distribution (OOD) inputs into in-distribution classes with high confidence.
We propose an alternative probabilistic paradigm that is both practically useful and theoretically viable for the OOD detection tasks.
arXiv Detail & Related papers (2022-09-26T15:59:55Z) - Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD
Training Data Estimate a Combination of the Same Core Quantities [104.02531442035483]
The goal of this paper is to recognize common objectives as well as to identify the implicit scoring functions of different OOD detection methods.
We show that binary discrimination between in- and (different) out-distributions is equivalent to several distinct formulations of the OOD detection problem.
We also show that the confidence loss which is used by Outlier Exposure has an implicit scoring function which differs in a non-trivial fashion from the theoretically optimal scoring function.
arXiv Detail & Related papers (2022-06-20T16:32:49Z) - Training OOD Detectors in their Natural Habitats [31.565635192716712]
Out-of-distribution (OOD) detection is important for machine learning models deployed in the wild.
Recent methods use auxiliary outlier data to regularize the model for improved OOD detection.
We propose a novel framework that leverages wild mixture data -- that naturally consists of both ID and OOD samples.
arXiv Detail & Related papers (2022-02-07T15:38:39Z)
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.