DeceptionNet: Network-Driven Domain Randomization

By Sergey Zakharov, Wadim Kehl, Slobodan Ilic. 2019

100 citations recorded by the source corpus.

We present a novel approach to tackle domain adaptation between synthetic and real data. Instead, of employing "blind" domain randomization, i.e., augmenting synthetic renderings with random backgrounds or changing illumination and colorization, we leverage the task network as its own adversarial guide toward useful augmentations that maximize the uncertainty of the output. To this end, we design a min-max optimization scheme where a given task competes against a special deception network to minimize the task error subject to the specific constraints enforced by the deceiver. The deception network samples from a family of differentiable pixel-level perturbations and exploits the task architecture to find the most destructive augmentations. Unlike GAN-based approaches that require unlabeled data from the target domain, our method achieves robust mappings that scale well to multiple target distributions from source data alone. We apply our framework to the tasks of digit recognition on enhanced MNIST variants, classification and object pose estimation on the Cropped LineMOD dataset as well as semantic segmentation on the Cityscapes dataset and compare it to a number of domain adaptation approaches, thereby demonstrating similar results with superior generalization capabilities.

Subfields: Artificial Intelligence, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Solving Rubik's Cube with a Robot Hand (2019, background): “For vision models, domain randomization has been modified to improve image content diversity [50, 85, 21] and to adapt the distribution by using an adversarial network [120].”
Learning to Generate Novel Domains for Domain Generalization (2020, unknown): “ure of objects, background scenes, lighting conditions, etc. via a computer simulator [49]. Recently, DR has been successfully used in some computer vision applications, such as semantic segmentation [54,55] and vehicle detection for autonomous driving [42]. However, our approach is signicantly dier”
A Simple Semi-Supervised Learning Framework for Object Detection (2020, background): “…and those with data augmentation using diﬀerent amount of labeled training data on MS-COCO [30]. combination of basic image transformations, such as rotation, translation, ﬂip-ping, or color jittering, to neural image synthesis [68,21,62] and policies learned by reinforcement learning [6,69].”
FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space (2021, background): “Domain generalization [5, 9, 12, 14, 43, 47, 58, 59] aims to learn a model from multiple source domains such that it can directly generalize to unseen target domains.”
Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization (2020, methodology): “on methods proposed to generate synthetic images derived from the given multiple source domains to increase the diversity of the input images, so that the network could learn from a larger data space [49,50]. Another promising direction is to extract domain-invariant features over multiple source do”
Synthetic Data for Deep Learning (2019, background): “[682] look at a similar idea from the point of view of domain randomization (see also Section 5.”
Increasing generality in machine learning through procedural content generation (2019, background): “In the more sophisticated guided domain randomization, the type of randomization is inﬂuenced by its eﬀect on the training process [43, 28, 38, 44].”
Deep Template-based Object Instance Detection (2021, background): “The difficulty of gathering a real dataset can be partially alleviated using simple rendering techniques [14, 22, 30] combined with data augmentation such as random backgrounds and domain randomization [36, 43, 37], but still suffers from a domain gap with real images.”
Target-Independent Domain Adaptation for WBC Classification Using Generative Latent Search (2020, background): “We also compare with three Domain Randomization (DR) techniques, DR1 [38], DR2 [39] and DR3 [40].”