Validation of Simulation-Based Testing: Bypassing Domain Shift with Label-to-Image Synthesis

• URL: http://arxiv.org/abs/2106.05549v1
• Date: Thu, 10 Jun 2021 07:23:58 GMT
• Title: Validation of Simulation-Based Testing: Bypassing Domain Shift with Label-to-Image Synthesis
• Authors: Julia Rosenzweig, Eduardo Brito, Hans-Ulrich Kobialka, Maram Akila, Nico M. Schmidt, Peter Schlicht, Jan David Schneider, Fabian H\"uger, Matthias Rottmann, Sebastian Houben, Tim Wirtz
• Abstract summary: We propose a novel framework consisting of a generative label-to-image synthesis model together with different transferability measures. We validate our approach empirically on a semantic segmentation task on driving scenes. Although the latter can distinguish between real-life and synthetic tests, in the former we observe surprisingly strong correlations of 0.7 for both cars and pedestrians.
• Score: 9.531148049378672
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many machine learning applications can benefit from simulated data for systematic validation - in particular if real-life data is difficult to obtain or annotate. However, since simulations are prone to domain shift w.r.t. real-life data, it is crucial to verify the transferability of the obtained results. We propose a novel framework consisting of a generative label-to-image synthesis model together with different transferability measures to inspect to what extent we can transfer testing results of semantic segmentation models from synthetic data to equivalent real-life data. With slight modifications, our approach is extendable to, e.g., general multi-class classification tasks. Grounded on the transferability analysis, our approach additionally allows for extensive testing by incorporating controlled simulations. We validate our approach empirically on a semantic segmentation task on driving scenes. Transferability is tested using correlation analysis of IoU and a learned discriminator. Although the latter can distinguish between real-life and synthetic tests, in the former we observe surprisingly strong correlations of 0.7 for both cars and pedestrians.

Related papers

• Exploring Generative AI for Sim2Real in Driving Data Synthesis [6.769182994217369]
  Driving simulators offer a solution by automatically generating various driving scenarios with corresponding annotations, but the simulation-to-reality (Sim2Real) domain gap remains a challenge. This paper applied three different generative AI methods to leverage semantic label maps from a driving simulator as a bridge for the creation of realistic datasets. Experiments show that although GAN-based methods are adept at generating high-quality images when provided with manually annotated labels, ControlNet produces synthetic datasets with fewer artefacts and more structural fidelity when using simulator-generated labels.
  arXiv  Detail & Related papers  (2024-04-14T01:23:19Z)
• Reliability in Semantic Segmentation: Can We Use Synthetic Data? [69.28268603137546]
  We show for the first time how synthetic data can be specifically generated to assess comprehensively the real-world reliability of semantic segmentation models. This synthetic data is employed to evaluate the robustness of pretrained segmenters. We demonstrate how our approach can be utilized to enhance the calibration and OOD detection capabilities of segmenters.
  arXiv  Detail & Related papers  (2023-12-14T18:56:07Z)
• ParGANDA: Making Synthetic Pedestrians A Reality For Object Detection [2.7648976108201815]
  We propose to use a Generative Adversarial Network (GAN) to close the gap between the real and synthetic data. Our approach not only produces visually plausible samples but also does not require any labels of the real domain.
  arXiv  Detail & Related papers  (2023-07-21T05:26:32Z)
• HaDR: Applying Domain Randomization for Generating Synthetic Multimodal Dataset for Hand Instance Segmentation in Cluttered Industrial Environments [0.0]
  This study uses domain randomization to generate a synthetic RGB-D dataset for training multimodal instance segmentation models. We show that our approach enables the models to outperform corresponding models trained on existing state-of-the-art datasets.
  arXiv  Detail & Related papers  (2023-04-12T13:02:08Z)
• Revisiting the Evaluation of Image Synthesis with GANs [55.72247435112475]
  This study presents an empirical investigation into the evaluation of synthesis performance, with generative adversarial networks (GANs) as a representative of generative models. In particular, we make in-depth analyses of various factors, including how to represent a data point in the representation space, how to calculate a fair distance using selected samples, and how many instances to use from each set.
  arXiv  Detail & Related papers  (2023-04-04T17:54:32Z)
• A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation [42.2398858786125]
  Deep learning in computer vision has achieved great success with the price of large-scale labeled training data. The uncontrollable data collection process produces non-IID training and test data, where undesired duplication may exist. To circumvent them, an alternative is to generate synthetic data via 3D rendering with domain randomization.
  arXiv  Detail & Related papers  (2023-03-16T09:03:52Z)
• One-Shot Domain Adaptive and Generalizable Semantic Segmentation with Class-Aware Cross-Domain Transformers [96.51828911883456]
  Unsupervised sim-to-real domain adaptation (UDA) for semantic segmentation aims to improve the real-world test performance of a model trained on simulated data. Traditional UDA often assumes that there are abundant unlabeled real-world data samples available during training for the adaptation. We explore the one-shot unsupervised sim-to-real domain adaptation (OSUDA) and generalization problem, where only one real-world data sample is available.
  arXiv  Detail & Related papers  (2022-12-14T15:54:15Z)
• Differentiable Agent-based Epidemiology [71.81552021144589]
  We introduce GradABM: a scalable, differentiable design for agent-based modeling that is amenable to gradient-based learning with automatic differentiation. GradABM can quickly simulate million-size populations in few seconds on commodity hardware, integrate with deep neural networks and ingest heterogeneous data sources.
  arXiv  Detail & Related papers  (2022-07-20T07:32:02Z)
• A Scaling Law for Synthetic-to-Real Transfer: A Measure of Pre-Training [52.93808218720784]
  Synthetic-to-real transfer learning is a framework in which we pre-train models with synthetically generated images and ground-truth annotations for real tasks. Although synthetic images overcome the data scarcity issue, it remains unclear how the fine-tuning performance scales with pre-trained models. We observe a simple and general scaling law that consistently describes learning curves in various tasks, models, and complexities of synthesized pre-training data.
  arXiv  Detail & Related papers  (2021-08-25T02:29:28Z)
• Learning summary features of time series for likelihood free inference [93.08098361687722]
  We present a data-driven strategy for automatically learning summary features from time series data. Our results indicate that learning summary features from data can compete and even outperform LFI methods based on hand-crafted values.
  arXiv  Detail & Related papers  (2020-12-04T19:21:37Z)

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.