Oliver Rippel

Mr. Oliver Rippel

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 July 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Open access
OROliver Rippel
Oliver Rippel
PMPatrick Mertens
Patrick Mertens
EKEike Konig
Eike Konig
DMDorit Merhof
Dorit Merhof
Anomaly detection (AD) in images is a fundamental computer vision problem and refers to identifying images that deviate significantly from normality. State-of-the-art AD algorithms commonly learn a model of normality from scratch using task-specific datasets in either semisupervised or self-supervised manner. We follow an alternative approach and model the distribution of normal data in deep feature representations learned from ImageNet via a multivariate Gaussian (MVG). This lightweight approach achieves a new state of the art in AD on the public MVTec AD dataset. In addition to the empirical benefits, we give a clear motivation for the seemingly simplistic approach via the ties between deep generative and discriminative modeling revealed recently. We further elucidate why ImageNet representations are discriminative in the transfer learning AD setting using the principal component analysis. Here, we find that the principal components containing little variance in normal data are the ones crucial for discriminating between normal and anomalous instances, giving an explanation for the unreasonable effectiveness of our approach. We also investigate setting the working point of our approach by selecting acceptable false-positive rate thresholds based on the MVG assumption and the resistance of our approach to unlabeled anomalies in the dataset. Finally, we investigate whether our approach is prone to exploiting spurious correlations using explainable AI techniques. Code is publicly available at https://github.com/ORippler/gaussian-ad-mvtec.

31 March 2023
Verified
Book Chapter
Open access
PDF file
OROliver Rippel
Oliver Rippel
DMDorit Merhof
Dorit Merhof
Anomaly detection (AD) methods that are based on deep learning (DL) have considerably improved the state of the art in AD performance on natural images recently. Combined with the public release of large-scale datasets that target AD for automated visual inspection (AVI), this has triggered the development of numerous, novel AD methods specific to AVI. However, with the rapid emergence of novel methods, the need to systematically categorize them arises. In this review, we perform such a categorization, and identify the underlying assumptions as well as working principles of DL-based AD methods that are geared towards AVI. We perform this for 2D AVI setups, and find that the majority of successful AD methods currently combines features generated by pre-training DL models on large-scale, natural image datasets with classical AD methods in hybrid AD schemes. Moreover, we give the main advantages and drawbacks of the two identified model categories in the context of AVI’s inherent requirements. Last, we outline open research questions, such as the need for an improved detection performance of semantic anomalies, and propose potential ways to address them.

23 June 2022 in Sensors
Verified
Journal Article
Open access
PDF file
OROliver Rippel
Oliver Rippel
CZCorinna Zwinge
Corinna Zwinge
DMDorit Merhof
Dorit Merhof
Fabric anomaly detection (AD) tries to detect anomalies (i.e., defects) in fabrics, and fabric AD approaches are continuously improved with respect to their AD performance. However, developed solutions are known to generalize poorly to previously unseen fabrics, posing a crucial limitation to their applicability. Moreover, current research focuses on adapting converged models to previously unseen fabrics in a post hoc manner, rather than training models that generalize better in the first place. In our work, we explore this potential for the first time. Specifically, we propose that previously unseen fabrics can be regarded as shifts in the underlying data distribution. We therefore argue that factors which reportedly improve a model’s resistance to distribution shifts should also improve the performance of supervised fabric AD methods on unseen fabrics. Hence, we assess the potential benefits of: (I) vicinal risk minimization (VRM) techniques adapted to the fabric AD use-case, (II) different loss functions, (III) ImageNet pre-training, (IV) dataset diversity, and (V) model architecture as well as model complexity. The subsequently performed large-scale analysis reveals that (I) only the VRM technique, AugMix, consistently improves performance on unseen fabrics; (II) hypersphere classifier outperforms other loss functions when combined with AugMix and (III) ImageNet pre-training, which is already beneficial on its own; (IV) increasing dataset diversity improves performance on unseen fabrics; and (V) architectures with better ImageNet performance also perform better on unseen fabrics, yet the same does not hold for more complex models. Notably, the results show that not all factors and techniques which reportedly improve a model’s resistance to distribution shifts in natural images also improve the generalization of supervised fabric AD methods to unseen fabrics, demonstrating the necessity of our work. Additionally, we also assess whether the performance gains of models which generalize better propagate to post hoc adaptation methods and show this to be the case. Since no suitable fabric dataset was publicly available at the time of this work, we acquired our own fabric dataset, called OLP, as the basis for the above experiments. OLP consists of 38 complex, patterned fabrics, more than 6400 images in total, and is made publicly available.

1 January 2022
Verified
Conference Paper
Open access
OROliver Rippel
Oliver Rippel
SGSergen Gülçelik
Sergen Gülçelik
KRKhosrow Rahimi
Khosrow Rahimi
JKJuliana Kurniadi
Juliana Kurniadi
AHAndreas Herrmann
Andreas Herrmann
DMDorit Merhof
Dorit Merhof

23 October 2020 in arXiv
Verified
Preprint
Open access
PDF file
OROliver Rippel
Oliver Rippel
PMPatrick Mertens
Patrick Mertens
DMDorit Merhof
Dorit Merhof
Anomaly Detection (AD) in images is a fundamental computer vision problem and refers to identifying images and image substructures that deviate significantly from the norm. Popular AD algorithms commonly try to learn a model of normality from scratch using task specific datasets, but are limited to semi-supervised approaches employing mostly normal data due to the inaccessibility of anomalies on a large scale combined with the ambiguous nature of anomaly appearance. We follow an alternative approach and demonstrate that deep feature representations learned by discriminative models on large natural image datasets are well suited to describe normality and detect even subtle anomalies in a transfer learning setting. Our model of normality is established by fitting a multivariate Gaussian (MVG) to deep feature representations of classification networks trained on ImageNet using normal data only. By subsequently applying the Mahalanobis distance as the anomaly score we outperform the current state of the art on the public MVTec AD dataset, achieving an AUROC value of $95.8 \pm 1.2$ (mean $\pm$ SEM) over all 15 classes. We further investigate why the learned representations are discriminative to the AD task using Principal Component Analysis. We find that the principal components containing little variance in normal data are the ones crucial for discriminating between normal and anomalous instances. This gives a possible explanation to the often sub-par performance of AD approaches trained from scratch using normal data only. By selectively fitting a MVG to these most relevant components only, we are able to further reduce model complexity while retaining AD performance. We also investigate setting the working point by selecting acceptable False Positive Rate thresholds based on the MVG assumption. Code available at https://github.com/ORippler/gaussian-ad-mvtec

13 June 2022 in arXiv
Verified
Preprint
Open access
PDF file
OROliver Rippel
Oliver Rippel
ACArnav Chavan
Arnav Chavan
CLChucai Lei
Chucai Lei
DMDorit Merhof
Dorit Merhof
Current state-of-the-art anomaly detection (AD) methods exploit the powerful representations yielded by large-scale ImageNet training. However, catastrophic forgetting prevents the successful fine-tuning of pre-trained representations on new datasets in the semi-supervised setting, and representations are therefore commonly fixed. In our work, we propose a new method to overcome catastrophic forgetting and thus successfully fine-tune pre-trained representations for AD in the transfer learning setting. Specifically, we induce a multivariate Gaussian distribution for the normal class based on the linkage between generative and discriminative modeling, and use the Mahalanobis distance of normal images to the estimated distribution as training objective. We additionally propose to use augmentations commonly employed for vicinal risk minimization in a validation scheme to detect onset of catastrophic forgetting. Extensive evaluations on the public MVTec dataset reveal that a new state of the art is achieved by our method in the AD task while simultaneously achieving anomaly segmentation performance comparable to prior state of the art. Further, ablation studies demonstrate the importance of the induced Gaussian distribution as well as the robustness of the proposed fine-tuning scheme with respect to the choice of augmentations.