# DeceptionNet: Network-Driven Domain Randomization

arXiv: https://arxiv.org/abs/1904.02750 · HTML: https://mlsanity.com/paper/1904.02750/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

## Built on by (most cited first, 30 of 43)

- [FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space](https://mlsanity.com/paper/2103.06030/) (2021)
- [ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation](https://mlsanity.com/paper/2203.09418/) (2022)
- [Invariant Information Bottleneck for Domain Generalization](https://mlsanity.com/paper/2106.06333/) (2021)
- [Sparse Mixture-of-Experts are Domain Generalizable Learners](https://mlsanity.com/paper/2206.04046/) (2022)
- [SPEED+: Next-Generation Dataset for Spacecraft Pose Estimation across Domain Gap](https://mlsanity.com/paper/2110.03101/) (2021)
- [Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects](https://mlsanity.com/paper/2208.03792/) (2022)
- [Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalization](https://mlsanity.com/paper/2112.11177/) (2021)
- [Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization](https://mlsanity.com/paper/2108.08596/) (2021)
- [On-Demand Sampling: Learning Optimally from Multiple Distributions](https://mlsanity.com/paper/2210.12529/) (2022)
- [Feature-based Style Randomization for Domain Generalization](https://mlsanity.com/paper/2106.03171/) (2021)
- [Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation](https://mlsanity.com/paper/2203.10339/) (2022)
- [CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation](https://mlsanity.com/paper/2402.14795/) (2024)
- [Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation](https://mlsanity.com/paper/2307.07907/) (2023)
- [TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimation](https://mlsanity.com/paper/2212.12902/) (2022)
- [Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive Learning](https://mlsanity.com/paper/2111.10827/) (2021)
- [Distributionally Robust Policy Learning via Adversarial Environment Generation](https://mlsanity.com/paper/2107.06353/) (2021)
- [Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image Restoration](https://mlsanity.com/paper/2208.03901/) (2022)
- [Rapid Motor Adaptation for Robotic Manipulator Arms](https://mlsanity.com/paper/2312.04670/) (2023)
- [Learning Feasibility to Imitate Demonstrators with Different Dynamics](https://mlsanity.com/paper/2110.15142/) (2021)
- [Weakly Supervised Correspondence Learning](https://mlsanity.com/paper/2203.00904/) (2022)
- [Physics-based Differentiable Depth Sensor Simulation](https://mlsanity.com/paper/2103.16563/) (2021)
- [Towards Domain-agnostic Depth Completion](https://mlsanity.com/paper/2207.14466/) (2022)
- [Bridging the Domain Gap for Flight-Ready Spaceborne Vision](https://mlsanity.com/paper/2409.11661/) (2024)
- [Learning from Imperfect Demonstrations via Adversarial Confidence Transfer](https://mlsanity.com/paper/2202.02967/) (2022)
- [Photo-realistic Neural Domain Randomization](https://mlsanity.com/paper/2210.12682/) (2022)
- [Indescribable Multi-modal Spatial Evaluator](https://mlsanity.com/paper/2303.00369/) (2023)
- [Cryo-shift: Reducing domain shift in cryo-electron subtomograms with unsupervised domain adaptation and randomization](https://mlsanity.com/paper/2111.09114/) (2021)
- [Domain Generalization for Mammographic Image Analysis with Contrastive Learning](https://mlsanity.com/paper/2304.10226/) (2023)
- [SD-Net: Symmetric-Aware Keypoint Prediction and Domain Adaptation for 6D Pose Estimation In Bin-picking Scenarios](https://mlsanity.com/paper/2403.09317/) (2024)
- [Learning from scarce information: using synthetic data to classify Roman fine ware pottery](https://mlsanity.com/paper/2107.01401/) (2021)

## Abstract (arXiv)

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.