On the Learnability of Out-of-distribution Detection
- URL: http://arxiv.org/abs/2404.04865v1
- Date: Sun, 7 Apr 2024 08:17:48 GMT
- Title: On the Learnability of Out-of-distribution Detection
- Authors: Zhen Fang, Yixuan Li, Feng Liu, Bo Han, Jie Lu,
- Abstract summary: This paper investigates the probably approximately correct (PAC) learning theory of OOD detection.
We prove several impossibility theorems for the learnability of OOD detection under some scenarios.
We then give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios.
- Score: 46.9442031620796
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studied a more realistic setting: out-of-distribution (OOD) detection, where test data may come from classes that are unknown during training (i.e., OOD data). Due to the unavailability and diversity of OOD data, good generalization ability is crucial for effective OOD detection algorithms, and corresponding learning theory is still an open problem. To study the generalization of OOD detection, this paper investigates the probably approximately correct (PAC) learning theory of OOD detection that fits the commonly used evaluation metrics in the literature. First, we find a necessary condition for the learnability of OOD detection. Then, using this condition, we prove several impossibility theorems for the learnability of OOD detection under some scenarios. Although the impossibility theorems are frustrating, we find that some conditions of these impossibility theorems may not hold in some practical scenarios. Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios. Lastly, we offer theoretical support for representative OOD detection works based on our OOD theory.
Related papers
- Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution [38.844580833635725]
We present a training-time regularization technique to mitigate the bias and boost imbalanced OOD detectors across architecture designs.
Our method translates into consistent improvements on the representative CIFAR10-LT, CIFAR100-LT, and ImageNet-LT benchmarks.
arXiv Detail & Related papers (2024-07-23T12:28:59Z) - Can Pre-trained Networks Detect Familiar Out-of-Distribution Data? [37.36999826208225]
We study the effect of PT-OOD on the OOD detection performance of pre-trained networks.
We find that the low linear separability of PT-OOD in the feature space heavily degrades the PT-OOD detection performance.
We propose a unique solution to large-scale pre-trained models: Leveraging powerful instance-by-instance discriminative representations of pre-trained models.
arXiv Detail & Related papers (2023-10-02T02:01:00Z) - Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for
Out-of-Domain Detection [28.810524375810736]
Out-of-distribution (OOD) detection is a critical task for reliable predictions over text.
Fine-tuning with pre-trained language models has been a de facto procedure to derive OOD detectors.
We show that using distance-based detection methods, pre-trained language models are near-perfect OOD detectors when the distribution shift involves a domain change.
arXiv Detail & Related papers (2023-05-22T17:42:44Z) - Open-World Continual Learning: Unifying Novelty Detection and Continual
Learning [13.186315474669287]
This paper theoretically proves that OOD detection actually is necessary for CIL.
A good CIL algorithm based on our theory can naturally be used in open world learning.
New CIL methods are also designed, which outperform strong baselines in terms of CIL accuracy and its continual OOD detection by a large margin.
arXiv Detail & Related papers (2023-04-20T01:32:32Z) - Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is
All You Need [52.88953913542445]
We find surprisingly that simply using reconstruction-based methods could boost the performance of OOD detection significantly.
We take Masked Image Modeling as a pretext task for our OOD detection framework (MOOD)
arXiv Detail & Related papers (2023-02-06T08:24:41Z) - Is Out-of-Distribution Detection Learnable? [45.377641783085046]
We investigate the probably approximately correct (PAC) learning theory of OOD detection.
We prove several impossibility theorems for the learnability of OOD detection under some scenarios.
We then give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios.
arXiv Detail & Related papers (2022-10-26T13:35:19Z) - Pseudo-OOD training for robust language models [78.15712542481859]
OOD detection is a key component of a reliable machine-learning model for any industry-scale application.
We propose POORE - POsthoc pseudo-Ood REgularization, that generates pseudo-OOD samples using in-distribution (IND) data.
We extensively evaluate our framework on three real-world dialogue systems, achieving new state-of-the-art in OOD detection.
arXiv Detail & Related papers (2022-10-17T14:32:02Z) - 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) - ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining [51.19164318924997]
Adrial Training with informative Outlier Mining improves robustness of OOD detection.
ATOM achieves state-of-the-art performance under a broad family of classic and adversarial OOD evaluation tasks.
arXiv Detail & Related papers (2020-06-26T20:58:05Z)
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.