Summary of Rosar: An Adversarial Re-training Framework For Robust Side-scan Sonar Object Detection, by Martin Aubard et al.
ROSAR: An Adversarial Re-Training Framework for Robust Side-Scan Sonar Object Detection
by Martin Aubard, László Antal, Ana Madureira, Luis F. Teixeira, Erika Ábrahám
First submitted to arxiv on: 14 Oct 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Robotics (cs.RO)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The novel framework, ROSAR, enhances the robustness of deep learning object detection models tailored for side-scan sonar (SSS) images. By integrating knowledge distillation with adversarial retraining, ROSAR addresses model efficiency and robustness against SSS noises. The paper introduces three novel datasets capturing different sonar setups and noise conditions. Two SSS safety properties are formalized to generate adversarial datasets for retraining. A comparative analysis of projected gradient descent (PGD) and patch-based attacks demonstrates significant improvements in model robustness and detection accuracy under SSS-specific conditions, enhancing the model’s robustness by up to 1.85%. ROSAR is available at this URL. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary ROSAR is a new way to make computer vision models better for underwater sonar images. Right now, these models can be tricked by noise in the sonar signals. ROSAR makes them more reliable and accurate. The researchers created three new datasets of sonar images with different types of noise to test their approach. They also came up with two rules for what makes a sonar image safe or not. This helped them make an adversarial dataset to train their model. In the end, they showed that ROSAR can improve model performance by 1.85% and accuracy by making them more robust against underwater sonar noise. |
Keywords
» Artificial intelligence » Deep learning » Gradient descent » Knowledge distillation » Object detection
