Pith. sign in

REVIEW 3 cited by

Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1810.10093 v2 pith:O3WPGLZ2 submitted 2018-10-23 cs.CV

Aayush Prakash , Shaad Boochoon , Mark Brophy , David Acuna , Eric Cameracci , Gavriel State , Omer Shapira , Stan Birchfield This is my paper · ORCID
classification cs.CV
keywords datadomainrealsynthetickittirandomizationaccordingcontext
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We present structured domain randomization (SDR), a variant of domain randomization (DR) that takes into account the structure and context of the scene. In contrast to DR, which places objects and distractors randomly according to a uniform probability distribution, SDR places objects and distractors randomly according to probability distributions that arise from the specific problem at hand. In this manner, SDR-generated imagery enables the neural network to take the context around an object into consideration during detection. We demonstrate the power of SDR for the problem of 2D bounding box car detection, achieving competitive results on real data after training only on synthetic data. On the KITTI easy, moderate, and hard tasks, we show that SDR outperforms other approaches to generating synthetic data (VKITTI, Sim 200k, or DR), as well as real data collected in a different domain (BDD100K). Moreover, synthetic SDR data combined with real KITTI data outperforms real KITTI data alone.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data

    cs.CV 2019-09 conditional novelty 6.0 of 10

    Stylizing synthetic images with real-world styles and enforcing pyramid consistency lets a segmentation network generalize from simulation to unseen real street scenes without target data.

  2. Training Deep Learning Models via Synthetic Data: Application in Unmanned Aerial Vehicles

    cs.CV 2019-08 conditional novelty 4.0 of 10

    A proof-of-concept that synthetic images can train deep models for two drone image tasks, forest-fire classification and house counting, with no independent test of generalization.

  3. Conditional Generative Adversarial Networks for Data Augmentation and Adaptation in Remotely Sensed Imagery

    cs.CV 2019-08 conditional novelty 4.0 of 10

    Chaining a progressive GAN (for segmentation labels) and a conditional GAN (for imagery), the paper shows vehicle detection mAP improves by up to roughly 10% relative when augmenting very small Potsdam training sets w...

Pith tools