Summary of Coreset Selection For Object Detection, by Hojun Lee et al.
Coreset Selection for Object Detection
by Hojun Lee, Suyoung Kim, Junhoo Lee, Jaeyoung Yoo, Nojun Kwak
First submitted to arxiv on: 14 Apr 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
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 A novel approach to coreset selection for object detection is introduced, addressing a long-standing gap in research. Coreset Selection for Object Detection (CSOD) generates representative feature vectors for multiple objects of the same class within each image, considering both representativeness and diversity through submodular optimization. This technique outperforms random selection by +6.4%p in AP_{50} when selecting 200 images on the Pascal VOC dataset. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Coreset selection is a way to pick a small group of pictures that represents an entire collection. It’s been studied for image classification, but object detection is trickier because one picture can have many objects. So, scientists haven’t done much research on this yet. To fill the gap, we came up with a new method called Coreset Selection for Object Detection (CSOD). CSOD creates special vectors that describe each group of objects in an image. Then, it uses these vectors to pick the best subset. When we tested CSOD on some famous images, it did +6.4 better than picking random ones. |
Keywords
» Artificial intelligence » Image classification » Object detection » Optimization
