Summary of Yolooc: Yolo-based Open-class Incremental Object Detection with Novel Class Discovery, by Qian Wan et al.
YOLOOC: YOLO-based Open-Class Incremental Object Detection with Novel Class Discovery
by Qian Wan, Xiang Xiang, Qinhao Zhou
First submitted to arxiv on: 30 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Image and Video Processing (eess.IV)
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 proposes a new approach to open-world object detection (OWOD) that can detect novel classes and incrementally learn them without forgetting previously known classes. The challenge lies in detecting novel classes at inference stage, which is different from previous approaches that rely on strongly-supervised or weakly-supervised data. To address this, the paper introduces a new benchmark that simulates real-world scenarios where novel classes are only encountered during inference. The proposed OWOD detector, YOLOOC, uses label smoothing to prevent over-confidence and discover novel classes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers aim to improve open-world object detection by developing a model that can learn from novel classes without forgetting previously known ones. They create a new benchmark that reflects real-world scenarios where novel classes are only encountered during inference. The proposed YOLOOC detector uses label smoothing to prevent over-confidence and discover novel classes. |
Keywords
» Artificial intelligence » Inference » Object detection » Supervised
