Summary of Knowledge Distillation in Yolox-vit For Side-scan Sonar Object Detection, by Martin Aubard et al.
Knowledge Distillation in YOLOX-ViT for Side-Scan Sonar Object Detection
by Martin Aubard, László Antal, Ana Madureira, Erika Ábrahám
First submitted to arxiv on: 14 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 YOLOX-ViT, a novel object detection model, is presented in this paper. The research investigates the effectiveness of knowledge distillation for reducing model size without sacrificing performance, specifically in underwater robotics. A new side-scan sonar image dataset is introduced and used to evaluate the object detector’s performance. Results show that knowledge distillation effectively reduces false positives in wall detection and improves object detection accuracy in the underwater environment. The visual transformer layer significantly improves accuracy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this paper, scientists developed a new way to detect objects underwater using special machines called robots. They wanted to see if they could make these robots better by teaching them how to be more accurate without making them bigger or slower. To do this, they created a new type of computer model and tested it on some underwater images. The results were great – the robot got much better at detecting things like walls and objects. This is important because underwater robots can help us explore and protect our oceans. |
Keywords
» Artificial intelligence » Knowledge distillation » Object detection » Transformer » Vit
