Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders

Moller, Felix; Botache, Diego; Huseljic, Denis; Heidecker, Florian; Bieshaar, Maarten; Sick, Bernhard

doi:10.1109/cvprw53098.2021.00014

Cited by 18 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, if a real-world energy dataset consists only of European energy data, the synthetic households will also reflect the characteristics of European households. This is referred to as the out-of-distribution (OOD) generalization problem [186], a well-known challenge when working with synthetic data [187]. The OOD problem describes a situation where the data distribution of the test dataset is not identical to the data distribution of the training dataset when developing ML models.…”

Section: Fairnessmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on the Use of Synthetic Data for Enhancing Key Aspects of Trustworthy AI in the Energy Domain: Challenges and Opportunities

Meiser,

Zinnikus

2024

Energies

View full text Add to dashboard Cite

To achieve the energy transition, energy and energy efficiency are becoming more and more important in society. New methods, such as Artificial Intelligence (AI) and Machine Learning (ML) models, are needed to coordinate supply and demand and address the challenges of the energy transition. AI and ML are already being applied to a growing number of energy infrastructure applications, ranging from energy generation to energy forecasting and human activity recognition services. Given the rapid development of AI and ML, the importance of Trustworthy AI is growing as it takes on increasingly responsible tasks. Particularly in the energy domain, Trustworthy AI plays a decisive role in designing and implementing efficient and reliable solutions. Trustworthy AI can be considered from two perspectives, the Model-Centric AI (MCAI) and the Data-Centric AI (DCAI) approach. We focus on the DCAI approach, which relies on large amounts of data of sufficient quality. These data are becoming more and more synthetically generated. To address this trend, we introduce the concept of Synthetic Data-Centric AI (SDCAI). In this survey, we examine Trustworthy AI within a Synthetic Data-Centric AI context, focusing specifically on the role of simulation and synthetic data in enhancing the level of Trustworthy AI in the energy domain.

show abstract

Section: Fairnessmentioning

confidence: 99%

“…The OOD problem describes a situation where the data distribution of the test dataset is not identical to the data distribution of the training dataset when developing ML models. Synthetic data allow augmenting data, thus, reducing the OOD problem [187].…”

Section: Fairnessmentioning

confidence: 99%

A Survey on the Use of Synthetic Data for Enhancing Key Aspects of Trustworthy AI in the Energy Domain: Challenges and Opportunities

Meiser,

Zinnikus

2024

Energies

View full text Add to dashboard Cite

show abstract

“…Some caution is needed with unknown data samples because the model has never processed this data sample, and it is impossible to determine what will happen. Therefore, novel data samples and the analysis of whether they are part of the already known data (indistribution) or not (out-of-distribution) [41,42] are of great interest for model training and the validation of ML models.…”

Section: Noveltymentioning

confidence: 99%

“…The response of the ML model should be consistent and not give inconsistent prediction results. This behavior can also be applied to the feature space, e.g., a variational autoencoder [41] that has learned a data representation, where similar inputs should also be mapped to similar representations.…”

Section: Inconsistencymentioning

confidence: 99%

Corner cases in machine learning processes

Heidecker,

Bieshaar,

Sick

2024

AI Perspect. Adv.

Self Cite

View full text Add to dashboard Cite

Applications using machine learning (ML), such as highly autonomous driving, depend highly on the performance of the ML model. The data amount and quality used for model training and validation are crucial. If the model cannot detect and interpret a new, rare, or perhaps dangerous situation, often referred to as a corner case, we will likely blame the data for not being good enough or too small in number. However, the implemented ML model and its associated architecture also influence the behavior. Therefore, the occurrence of prediction errors resulting from the ML model itself is not surprising. This work addresses a corner case definition from an ML model’s perspective to determine which aspects must be considered. To achieve this goal, we present an overview of properties for corner cases that are beneficial for the description, explanation, reproduction, or synthetic generation of corner cases. To define ML corner cases, we review different considerations in the literature and summarize them in a general description and mathematical formulation, whereby the expected relevance-weighted loss is the key to distinguishing corner cases from common data. Moreover, we show how to operationalize the corner case characteristics to determine the value of a corner case. To conclude, we present the extended taxonomy for ML corner cases by adding the input, model, and deployment levels, considering the influence of the corner case properties.

show abstract

“…The approach of Möller et al [15] proposes a novel approach to generate out-of-distribution (OOD) datasets.The generated OOD samples are based on in-distribution datasets using methods like Gaussian Hyperspheric Offset and Soft Brownian Offset. The purpose is to enhance OOD detection and validate the generalization performance of neural networks.…”

Section: Simulation Engines and Acquisition Strategiesmentioning

confidence: 99%

Synthetic Dataset Acquisition for a Specific Target Domain

Niemeijer,

Mittal,

Brox

2023

2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

Intelligent sampling from simulation becomes crucial due to storage and hardware constraints. This research focuses on developing an intelligent acquisition strategy for synthetic data and evaluates multiple approaches to address the limitations of existing domain adaptation methods. Selecting suitable synthetic data for real-world model training presents challenges, as accurately representing the real world remains elusive. We tackle the task of adapting from synthetic to real-world data through unsupervised domain adaptation, a challenging setting for perception systems. The performance of our acquisition function is measured by its facilitation of this adaptation.We showcase different strategies, to assign value to synthetic images. Acquisition functions either operate based on synthetic data alone or take the given real world target domain into account, to assign a value to synthetic images. Leveraging assumptions from semi-supervised learning, we identify challenging real-world images and find their counterparts in the synthetic world. Evaluation is conducted using the GTA-5 dataset as the representative synthetic world and the Cityscapes and ACDC dataset as the target domain. State-of-the-art unsupervised domain adaptation approaches are employed to assess the effectiveness of our acquisition function.By advancing the utilization of synthetic data in training perception systems, this research contributes to improved real-world performance. Our findings demonstrate the potential of intelligent acquisition strategies for enhancing the adaptation from synthetic to real-world domains.

show abstract

Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders

Cited by 18 publications

References 7 publications

A Survey on the Use of Synthetic Data for Enhancing Key Aspects of Trustworthy AI in the Energy Domain: Challenges and Opportunities

A Survey on the Use of Synthetic Data for Enhancing Key Aspects of Trustworthy AI in the Energy Domain: Challenges and Opportunities

Corner cases in machine learning processes

Synthetic Dataset Acquisition for a Specific Target Domain

Contact Info

Product

Resources

About