A Simple Domain Shifting Network for Generating Low Quality Images

Guruprasad M. Hegde, Avinash Nittur Ramesh, Kanchana Vaishnavi Gandikota, Roman Obermaisser, Michael Moeller

Abstract

Deep learning models are typically trained on high-resolution, high-quality image datasets. However, when deployed on low-cost robotic hardware equipped with inexpensive sensors, these models often suffer from a significant performance drop due to the "domain gap" between pristine training data and noisy real-world input. This paper proposes a simple yet effective Domain Shifting Network (DSN) that learns to degrade high-quality images to mimic the specific distortions of low-cost cameras. By training classifiers on a combination of original and synthetically "ruined" images, the authors achieve substantial accuracy improvements on robotic hardware without requiring large, labeled target-domain datasets.

Introduction

In the field of computer vision, there exists a persistent "quality gap." While state-of-the-art models are trained on "champagne" data—high-resolution, perfectly exposed images from the web—they are frequently expected to perform on "beer" hardware—the noisy, low-dynamic-range cameras found on affordable robots like the Anki Cozmo. When a model trained on ImageNet encounters the specific noise, blur, and color shifts of a €100 robot's sensor, its performance typically plummets.

To address this, researchers from the University of Siegen propose a pragmatic shift in perspective: rather than attempting to improve the robot's images, we should purposefully degrade our training data to match the robot's limitations.

Methodology: The Domain Shifting Network

The authors introduce a "Domain Shifting Network" designed to bridge the domain gap through a simple regression-based approach rather than complex adversarial training.

Data Collection: The "Screen-to-Camera" Trick

To teach a network how a specific robot "sees," the researchers developed a straightforward data collection method. They displayed high-resolution images from the Pascal VOC dataset on a high-quality screen and recorded them using the robot's low-quality camera. This process creates a perfectly paired dataset of "clean" originals and "noisy" robot-captured versions.

The experimental setup showing the Anki Cozmo robot capturing images displayed on a screen to create a paired dataset.

Network Architecture and Training

The DSN is a lightweight 4-layer convolutional regression network. Unlike Generative Adversarial Networks (GANs), which can be unstable, the DSN simply minimizes the pixel-wise $L_2$ loss between its output and the real robot-captured image. Once trained, this network acts as a "shifter" that can transform any high-quality image into a version that mimics the target hardware's specific noise profile.

Experimental Results

The researchers evaluated their approach using several datasets, including Asirra (cats vs. dogs) and a 5-class subset of ImageNet. They also created a "Cozmo in the Wild" test set by photographing printed images under various real-world conditions.

Qualitative comparison showing original images (left), the output of the Domain Shifting Network (middle), and real images captured by the robot (right).

The results demonstrate the effectiveness of the DSN:

  • 2-Way Classification: Accuracy on real robot images improved from 86.97% (baseline) to 94.24% using the adapted model.
  • 5-Way Classification: Accuracy rose from 73.49% to 76.39%.
  • Zero-Shot Capability: Notably, the DSN could be trained on one set of objects (Pascal VOC) and successfully applied to entirely different categories (Asirra), proving it learns the camera's characteristics rather than object-specific features.

Conclusion

The proposed Domain Shifting Network offers a simple, generic, and powerful scheme for adapting vision models to low-cost hardware. By focusing on the easier task of image degradation rather than restoration, the authors provide a robust path for deploying sophisticated AI on budget-friendly robotic platforms. Future work may extend this method to more complex tasks such as object detection and semantic segmentation.

Summary updated

Abstract

Deep Learning systems have proven to be extremely successful for image recognition tasks for which significant amounts of training data is available, e.g., on the famous ImageNet dataset. We demonstrate that for robotics applications with cheap camera equipment, the low image quality, however, influences the classification accuracy, and freely available data bases cannot be exploited in a straight forward way to train classifiers to be used on a robot. As a solution we propose to train a network on degrading the quality images in order to mimic specific low quality imaging systems. Numerical experiments demonstrate that classification networks trained by using images produced by our quality degrading network along with the high quality images outperform classification networks trained only on high quality data when used on a real robot system, while being significantly easier to use than competing zero-shot domain adaptation techniques.
BibTeX
@inproceedings{hegde2020simple,
  author = {Guruprasad M. Hegde and Avinash Nittur Ramesh and Kanchana Vaishnavi Gandikota and Roman Obermaisser and Michael Moeller},
  title = {{A Simple Domain Shifting Network for Generating Low Quality Images}},
  booktitle = {ICPR},
  year = {2020},
  url = {https://openreview.net/forum?id=15rTPcpw_CrQ},
}
Figure