Free Lunch for Generating Effective Outlier Supervision
- URL: http://arxiv.org/abs/2301.06657v2
- Date: Thu, 18 Jan 2024 02:10:39 GMT
- Title: Free Lunch for Generating Effective Outlier Supervision
- Authors: Sen Pei, Jiaxi Sun, Richard Yi Da Xu, Bin Fan, Shiming Xiang, and
Gaofeng Meng
- Abstract summary: 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.
- Score: 46.37464572099351
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: When deployed in practical applications, computer vision systems will
encounter numerous unexpected images (\emph{{i.e.}}, out-of-distribution data).
Due to the potentially raised safety risks, these aforementioned unseen data
should be carefully identified and handled. Generally, existing approaches in
dealing with out-of-distribution (OOD) detection mainly focus on the
statistical difference between the features of OOD and in-distribution (ID)
data extracted by the classifiers. Although many of these schemes have brought
considerable performance improvements, reducing the false positive rate (FPR)
when processing open-set images, they necessarily lack reliable theoretical
analysis and generalization guarantees. Unlike the observed ways, in this
paper, we investigate the OOD detection problem based on the Bayes rule and
present a convincing description of the reason for failures encountered by
conventional classifiers. Concretely, our analysis reveals that refining the
probability distribution yielded by the vanilla neural networks is necessary
for OOD detection, alleviating the issues of assigning high confidence to OOD
data. To achieve this effortlessly, we propose an ultra-effective method to
generate near-realistic outlier supervision. Extensive experiments on
large-scale benchmarks reveal that our proposed \texttt{BayesAug} significantly
reduces the FPR95 over 12.50\% compared with the previous schemes, boosting the
reliability of machine learning systems. The code will be made publicly
available.
Related papers
- Margin-bounded Confidence Scores for Out-of-Distribution Detection [2.373572816573706]
We propose a novel method called Margin bounded Confidence Scores (MaCS) to address the nontrivial OOD detection problem.
MaCS enlarges the disparity between ID and OOD scores, which in turn makes the decision boundary more compact.
Experiments on various benchmark datasets for image classification tasks demonstrate the effectiveness of the proposed method.
arXiv Detail & Related papers (2024-09-22T05:40:25Z) - 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) - Mitigating Overconfidence in Out-of-Distribution Detection by Capturing Extreme Activations [1.8531577178922987]
"Overconfidence" is an intrinsic property of certain neural network architectures, leading to poor OOD detection.
We measure extreme activation values in the penultimate layer of neural networks and then leverage this proxy of overconfidence to improve on several OOD detection baselines.
Compared to the baselines, our method often grants substantial improvements, with double-digit increases in OOD detection.
arXiv Detail & Related papers (2024-05-21T10:14:50Z) - Conservative Prediction via Data-Driven Confidence Minimization [70.93946578046003]
In safety-critical applications of machine learning, it is often desirable for a model to be conservative.
We propose the Data-Driven Confidence Minimization framework, which minimizes confidence on an uncertainty dataset.
arXiv Detail & Related papers (2023-06-08T07:05:36Z) - LINe: Out-of-Distribution Detection by Leveraging Important Neurons [15.797257361788812]
We introduce a new aspect for analyzing the difference in model outputs between in-distribution data and OOD data.
We propose a novel method, Leveraging Important Neurons (LINe), for post-hoc Out of distribution detection.
arXiv Detail & Related papers (2023-03-24T13:49:05Z) - Improving Out-of-Distribution Detection via Epistemic Uncertainty
Adversarial Training [29.4569172720654]
We develop a simple adversarial training scheme that incorporates an attack of the uncertainty predicted by the dropout ensemble.
We demonstrate this method improves OOD detection performance on standard data (i.e., not adversarially crafted), and improves the standardized partial AUC from near-random guessing performance to $geq 0.75$.
arXiv Detail & Related papers (2022-09-05T14:32:19Z) - Provably Robust Detection of Out-of-distribution Data (almost) for free [124.14121487542613]
Deep neural networks are known to produce highly overconfident predictions on out-of-distribution (OOD) data.
In this paper we propose a novel method where from first principles we combine a certifiable OOD detector with a standard classifier into an OOD aware classifier.
In this way we achieve the best of two worlds: certifiably adversarially robust OOD detection, even for OOD samples close to the in-distribution, without loss in prediction accuracy and close to state-of-the-art OOD detection performance for non-manipulated OOD data.
arXiv Detail & Related papers (2021-06-08T11:40:49Z) - 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) - Certifiably Adversarially Robust Detection of Out-of-Distribution Data [111.67388500330273]
We aim for certifiable worst case guarantees for OOD detection by enforcing low confidence at the OOD point.
We show that non-trivial bounds on the confidence for OOD data generalizing beyond the OOD dataset seen at training time are possible.
arXiv Detail & Related papers (2020-07-16T17:16:47Z) - 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.