Summary of Nbbox: Noisy Bounding Box Improves Remote Sensing Object Detection, by Yechan Kim et al.
NBBOX: Noisy Bounding Box Improves Remote Sensing Object Detection
by Yechan Kim, SooYeon Kim, Moongu Jeon
First submitted to arxiv on: 14 Sep 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 The paper presents an investigation into bounding box transformations as a data augmentation technique for remote sensing object detection, specifically in aerial imagery. The authors argue that traditional image-level augmentations may not be sufficient, given inconsistent bounding box annotations. They propose the NBBOX (Noise Injection into Bounding Box) strategy, which involves scaling, rotating, and translating bounding boxes. Experimental results on DOTA and DIOR-R datasets show significant improvements in object detection without additional processing or computational overhead. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study investigates a new way to improve remote sensing object detection by changing the shapes of objects on images. The researchers think that current methods might not work well because object boundaries can be tricky to define accurately. They created a new technique called NBBOX, which adjusts the position, size, and orientation of bounding boxes around objects. By doing so, they increased the accuracy of object detection without requiring extra computing power or complex processing. |
Keywords
» Artificial intelligence » Bounding box » Data augmentation » Object detection
